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

    Neuronpedia

    INDEX
    Explanations

    statistics and census data

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -FIRST
    -0.08
     lectures
    -0.07
    %),
    -0.07
     Ja
    -0.07
     d
    -0.07
     bash
    -0.07
     inspect
    -0.07
    -expanded
    -0.07
    _AMOUNT
    -0.07
    琥
    -0.06
    POSITIVE LOGITS
    文化和
    0.07
     cortisol
    0.07
    찧
    0.07
    ﹱ
    0.07
    촛
    0.07
    䲢
    0.07
     taxa
    0.07
    oxel
    0.06
    췰
    0.06
    讦
    0.06
    Act Density 0.064%

    No Known Activations