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

    Neuronpedia

    INDEX
    Explanations

    numbers after 0 or 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    3
    0.80
    5
    0.71
    7
    0.71
    1
    0.70
    n
    0.69
    d
    0.69
    2
    0.68
    4
    0.68
    0.66
    ৬০
    0.66
    POSITIVE LOGITS
    棰
    0.80
     loosely
    0.78
     soltanto
    0.77
    枨
    0.76
     Clouds
    0.75
    Beverungen
    0.74
    ‪‬
    0.74
     blatantly
    0.74
     solamente
    0.73
     Sistemi
    0.72
    Act Density 0.165%

    No Known Activations