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

    Neuronpedia

    INDEX
    Explanations

    out

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     paste
    -0.07
    -Key
    -0.06
     працю
    -0.06
    ographies
    -0.06
     porad
    -0.06
     "{}
    -0.06
     biggest
    -0.06
    ั
    -0.06
    .LayoutInflater
    -0.06
     Kır
    -0.06
    POSITIVE LOGITS
    กล
    0.06
    โปรแกรม
    0.06
    寒
    0.06
     uphol
    0.06
    _DELETE
    0.06
    confirmed
    0.06
    �乐
    0.06
    '=>$
    0.06
     ド
    0.06
     rallying
    0.06
    Act Density 0.000%

    No Known Activations