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

    Neuronpedia

    INDEX
    Explanations

    Ellipses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Jing
    -0.06
    Closed
    -0.06
     camps
    -0.06
    Cut
    -0.06
     Joker
    -0.06
     repet
    -0.06
    .total
    -0.06
    awah
    -0.06
     مطرح
    -0.06
    ㅋㅋㅋㅋ
    -0.06
    POSITIVE LOGITS
    office
    0.06
    -interface
    0.06
    LOY
    0.06
    +".
    0.06
    :inline
    0.06
    ैन
    0.06
    णन
    0.06
     arisen
    0.06
    _email
    0.06
    onation
    0.06
    Act Density 0.001%

    No Known Activations