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

    Neuronpedia

    INDEX
    Explanations

    occurrences of the word "on" in various contexts

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

    on the

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    gemini
    -0.44
    CardContent
    -0.43
     usarlo
    -0.43
    位
    -0.42
    Cordialement
    -0.42
    ///</
    -0.41
    ←
    -0.41
    CppMethod
    -0.40
    )))));
    -0.39
    twimg
    -0.39
    POSITIVE LOGITS
     behalf
    1.14
     occasion
    0.78
     the
    0.73
     ועל
    0.71
     weekends
    0.63
     horseback
    0.63
     occasions
    0.59
     a
    0.57
     Wednesdays
    0.57
     board
    0.56
    Act Density 0.329%

    No Known Activations