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

    Neuronpedia

    INDEX
    Explanations

    questions about the best

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    '
    0.89
    \
    0.86
    ’
    0.82
    0.75
    Where
    0.63
    G
    0.63
    ?\
    0.63
    OP
    0.61
    Em
    0.61
    The
    0.60
    POSITIVE LOGITS
     suited
    0.93
    suited
    0.83
     품질
    0.79
    iaire
    0.75
    immung
    0.73
    ниями
    0.70
    iality
    0.70
    iary
    0.68
     best
    0.67
     to
    0.64
    Act Density 0.109%

    No Known Activations