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

    Neuronpedia

    INDEX
    Explanations

    on

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Countdown
    -0.07
     Hubb
    -0.07
     countdown
    -0.07
    MLE
    -0.06
    Stmt
    -0.06
     Нас
    -0.06
     Israel
    -0.06
    zf
    -0.06
    ocracy
    -0.06
    н
    -0.06
    POSITIVE LOGITS
    .aggregate
    0.06
     vit
    0.06
     Ek
    0.06
    스티
    0.06
    ，更
    0.06
    .parseDouble
    0.06
    tickets
    0.06
     anonym
    0.06
     astonishing
    0.06
     legend
    0.06
    Act Density 0.020%

    No Known Activations