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

    Neuronpedia

    INDEX
    Explanations

    foreign other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ؔ
    0.65
     minimale
    0.59
    ^(
    0.58
    co
    0.56
    mathrm
    0.55
    com
    0.55
     minimal
    0.54
    ขอ
    0.54
    pc
    0.53
    «
    0.53
    POSITIVE LOGITS
     其他
    1.08
    ifical
    1.00
     anderer
    0.99
     altre
    0.98
     другая
    0.98
     otros
    0.96
     другим
    0.96
     而且
    0.95
     otras
    0.95
    Otros
    0.94
    Act Density 0.051%

    No Known Activations