Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    INDEX
    Explanations

    references to prediction and comparative behavior analysis in various contexts

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Past events, experiences, or history

    np_acts-logits-general · gemini-2.0-flash

    precedents and past experience

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Personendaten
    -0.43
     ब्रेकडाउन
    -0.40
    DataAnnotations
    -0.40
     RESPECT
    -0.40
     romantique
    -0.40
     TMPro
    -0.40
    sidemargin
    -0.40
     gesteld
    -0.39
    Jeografia
    -0.39
    AxisAlignment
    -0.38
    POSITIVE LOGITS
     precedents
    0.65
     precedent
    0.61
     experience
    0.54
    ">//
    0.52
    experience
    0.52
     experiences
    0.52
     precedenti
    0.49
     ujednoznacz
    0.49
     experien
    0.48
     precedente
    0.48
    Act Density 0.959%

    No Known Activations