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

    Neuronpedia

    INDEX
    Explanations

    believed to or imagine you

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    R
    0.83
     および
    0.82
    Y
    0.80
    Q
    0.77
    *.
    0.76
     Terbaru
    0.75
    選項
    0.73
    そして
    0.73
    Z
    0.72
    J
    0.72
    POSITIVE LOGITS
     that
    1.29
     having
    1.28
     there
    1.22
    <unused2197>
    1.22
     bahwa
    1.20
     أنه
    1.12
    <unused2204>
    1.10
     rằng
    1.09
    <unused336>
    1.08
     adanya
    1.08
    Act Density 1.711%

    No Known Activations