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

    Neuronpedia

    INDEX
    Explanations

    ,

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     TypeScript
    -0.07
     headquartered
    -0.06
     bổ
    -0.06
    γμα
    -0.06
    HG
    -0.06
    Initializer
    -0.06
    .HTTP
    -0.06
    اب
    -0.06
    引用
    -0.06
    服务
    -0.06
    POSITIVE LOGITS
     undercover
    0.08
    ٍ
    0.07
     CAB
    0.07
     Label
    0.06
    ΟΥΣ
    0.06
    _colour
    0.06
    lero
    0.06
    _LABEL
    0.06
     Beit
    0.06
    _Char
    0.06
    Act Density 0.334%

    No Known Activations