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

    Neuronpedia

    INDEX
    Explanations

    code, programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ಿತ್ಯ
    -0.08
     sive
    -0.08
     stat
    -0.07
     RET
    -0.07
     previous
    -0.07
     vorige
    -0.07
    _CONFIGURATION
    -0.07
    كر
    -0.07
     strategi
    -0.07
     ret
    -0.07
    POSITIVE LOGITS
     hormone
    0.10
    モデル
    0.10
    (attributes
    0.09
    保存
    0.09
     모델
    0.09
    属性
    0.09
    -save
    0.09
    .save
    0.09
    _save
    0.09
     ઑ
    0.08
    Act Density 0.002%

    No Known Activations