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

    Neuronpedia

    INDEX
    Explanations

    token

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     replica
    -0.07
    osten
    -0.07
    VIP
    -0.07
    /windows
    -0.07
    也不是
    -0.07
    蝮
    -0.06
    �
    -0.06
    ンド
    -0.06
     Master
    -0.06
     mast
    -0.06
    POSITIVE LOGITS
    馑
    0.08
    .WriteAllText
    0.08
     WPARAM
    0.08
     validation
    0.07
    .hstack
    0.07
     ammunition
    0.07
    จน
    0.07
    �
    0.07
    .propTypes
    0.07
    ihn
    0.07
    Act Density 0.002%

    No Known Activations