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

    Neuronpedia

    INDEX
    Explanations

    Question words, function words

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Richard
    -0.07
     情
    -0.07
     mappedBy
    -0.07
    央
    -0.06
     bahis
    -0.06
    Thursday
    -0.06
    _CLK
    -0.06
    薄
    -0.06
    Quant
    -0.06
     इ
    -0.06
    POSITIVE LOGITS
     squeeze
    0.07
     anno
    0.06
    EE
    0.06
    ELCOME
    0.06
     VIDEO
    0.06
    _prior
    0.06
    Ahead
    0.06
    _experiment
    0.06
     subscribing
    0.06
    เภ
    0.06
    Act Density 0.090%

    No Known Activations