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

    Neuronpedia

    INDEX
    Explanations

    Uncertainty, qualification, and reported speech

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    valuation
    -0.07
     Rod
    -0.07
    足
    -0.06
    握
    -0.06
    postData
    -0.06
    仰
    -0.06
    mania
    -0.06
     Aug
    -0.06
     buck
    -0.06
    -social
    -0.06
    POSITIVE LOGITS
    _REFERER
    0.07
     navigationOptions
    0.07
     whirl
    0.07
    _tD
    0.07
     dek
    0.06
     TextFormField
    0.06
     Ul
    0.06
     enctype
    0.06
     Victorian
    0.06
    ляд
    0.06
    Act Density 0.006%

    No Known Activations