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

    Neuronpedia

    INDEX
    Explanations

    start of turn

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     *
    0.81
     হলেও
    0.80
    0.80
     '
    0.80
     хвати
    0.79
     but
    0.79
     "
    0.77
     software
    0.75
     थोड़ा
    0.75
    OK
    0.74
    POSITIVE LOGITS
     artikel
    0.99
     kalimat
    0.97
    eminent
    0.96
    insight
    0.96
     podstawie
    0.95
    impse
    0.95
    newspaper
    0.94
    impresa
    0.94
    有哪些
    0.93
    izabeth
    0.93
    Act Density 0.791%

    No Known Activations