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

    Neuronpedia

    INDEX
    Explanations

    web routing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _EVAL
    -0.07
    (delta
    -0.07
    _PREVIEW
    -0.07
    .Orders
    -0.07
    .error
    -0.06
     ith
    -0.06
    �
    -0.06
    .Xml
    -0.06
     Alonso
    -0.06
     Virgin
    -0.06
    POSITIVE LOGITS
    业态
    0.07
    ekte
    0.07
     transparency
    0.07
    .encrypt
    0.07
     olmuştur
    0.07
     notorious
    0.07
    焰
    0.07
     매우
    0.07
    接入
    0.07
    _KEY
    0.07
    Act Density 0.018%

    No Known Activations