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

    Neuronpedia

    INDEX
    Explanations

    News and disasters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Sel
    -0.07
     patrol
    -0.07
    Hand
    -0.07
    _receiver
    -0.06
     Пар
    -0.06
    ラ
    -0.06
     Ú
    -0.06
     Wa
    -0.06
     Eva
    -0.06
     Middle
    -0.06
    POSITIVE LOGITS
    ahat
    0.07
    nets
    0.07
    :↵↵↵
    0.06
     cling
    0.06
     العامة
    0.06
     |>
    0.06
     가격
    0.06
     każ
    0.06
    split
    0.06
     trying
    0.06
    Act Density 0.082%

    No Known Activations