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

    Neuronpedia

    INDEX
    Explanations

    before after

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Posté
    -0.07
     Dealers
    -0.07
    ImageSharp
    -0.07
    _yes
    -0.07
    -top
    -0.07
    imeo
    -0.07
    �
    -0.07
    lectic
    -0.07
    pga
    -0.06
    หลายๆ
    -0.06
    POSITIVE LOGITS
     kaynağı
    0.07
    例
    0.07
    宫廷
    0.07
     kararı
    0.07
     sla
    0.07
     материал
    0.07
     ROOT
    0.07
     massac
    0.06
    rames
    0.06
     breaks
    0.06
    Act Density 0.045%

    No Known Activations