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

    Neuronpedia

    INDEX
    Explanations

    emojis and formatting characters

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ones
    0.61
    Grid
    0.60
    As
    0.58
    \},
    0.53
    onClick
    0.53
     tantas
    0.53
    asarray
    0.53
    el
    0.51
    inicio
    0.51
    getJSONObject
    0.51
    POSITIVE LOGITS
     و
    1.18
     그리고
    0.99
     etc
    0.93
     Diese
    0.92
     ای
    0.91
     無
    0.91
     Whether
    0.91
    などは
    0.91
     Beide
    0.91
     아무
    0.90
    Act Density 0.783%

    No Known Activations