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

    Neuronpedia

    INDEX
    Explanations

    listings and profiles

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bầu
    -0.07
     AQ
    -0.06
     сви
    -0.06
     Qgs
    -0.06
    	Connection
    -0.06
     способом
    -0.06
     आई
    -0.06
     strands
    -0.06
    ρέ
    -0.06
    Increases
    -0.06
    POSITIVE LOGITS
     ciz
    0.07
    bool
    0.07
    wick
    0.06
     [\
    0.06
     beliefs
    0.06
     biased
    0.06
    カテゴリ
    0.06
    esini
    0.06
     Alvarez
    0.06
    من
    0.06
    Act Density 0.020%

    No Known Activations