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

    Neuronpedia

    INDEX
    Explanations

    references to guidance and support in a collaborative work environment

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

    needing help or assistance

    np_acts-logits-general · gemini-2.0-flash

    requiring assistance or guidance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    complexContent
    -0.64
     Reactive
    -0.56
    antMatchers
    -0.53
    romolecules
    -0.52
    rtype
    -0.51
    hata
    -0.50
    Dati
    -0.50
    reactive
    -0.49
     Keim
    -0.49
    RetentionPolicy
    -0.49
    POSITIVE LOGITS
     assistance
    1.12
     assist
    0.98
    assistance
    0.97
     Assistance
    0.97
     guides
    0.97
     help
    0.94
    Assistance
    0.94
     assists
    0.91
     guide
    0.90
     guidance
    0.90
    Act Density 0.413%

    No Known Activations