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

    Neuronpedia

    INDEX
    Explanations

    at the top

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ;
    0.78
    (
    0.70
    :
    0.67
    はじ
    0.64
    ’
    0.63
    א
    0.63
    কি
    0.62
    મા
    0.60
     outsole
    0.58
    ও
    0.57
    POSITIVE LOGITS
    er
    0.79
    are
    0.78
    un
    0.74
    ruv
    0.73
    už
    0.69
    ilibre
    0.68
    nance
    0.66
    ার
    0.66
    انات
    0.66
    ar
    0.66
    Act Density 0.031%

    No Known Activations