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

    Neuronpedia

    INDEX
    Explanations

    phrases related to interpretation or inference in discussions

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

    drawing inferences from text

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    \{\\
    -0.42
    Identyfik
    -0.40
    tele
    -0.40
     protoimpl
    -0.38
    ]!='
    -0.38
    .*")]
    -0.36
    CreateModel
    -0.36
    ConstraintMaker
    -0.36
    hb
    -0.36
     tele
    -0.35
    POSITIVE LOGITS
     kasarigan
    0.68
    httphttps
    0.68
     interpretations
    0.52
     interpreta
    0.49
    interprétation
    0.48
     članak
    0.47
     inferences
    0.47
     interpretación
    0.46
     interpretation
    0.45
    LLocation
    0.45
    Act Density 0.098%

    No Known Activations