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

    Neuronpedia

    INDEX
    Explanations

    clean

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Şa
    -0.07
     Div
    -0.06
     his
    -0.06
    ళ
    -0.06
     cultivating
    -0.06
    꼽
    -0.06
     smuggling
    -0.06
    沟
    -0.06
    箕
    -0.06
    泄
    -0.06
    POSITIVE LOGITS
    .result
    0.07
    inline
    0.07
    روا
    0.07
    inform
    0.07
    _FUNCTIONS
    0.06
    or
    0.06
    redentials
    0.06
    /en
    0.06
    ffee
    0.06
    eters
    0.06
    Act Density 0.008%

    No Known Activations