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

    Neuronpedia

    INDEX
    Explanations

    questions seeking context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     splendid
    0.76
     (".
    0.76
     ('
    0.73
    ~(\
    0.72
    攏
    0.70
     ইচ্ছা
    0.69
    award
    0.69
    ídio
    0.68
    decoded
    0.68
     cardiomyocyte
    0.68
    POSITIVE LOGITS
     Knowing
    1.31
    Knowing
    1.23
     knowing
    1.04
    knowing
    1.03
    ?
    1.02
    ).
    0.93
     –
    0.92
     Einfluss
    0.90
     Trying
    0.90
     Influence
    0.89
    Act Density 0.181%

    No Known Activations