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

    Neuronpedia

    INDEX
    Explanations

    religious texts

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    IRCLE
    -0.07
    .Persistence
    -0.07
    -0.07
     Eli
    -0.07
    -0.07
    MAIN
    -0.06
    -0.06
    虸
    -0.06
    .DATA
    -0.06
    EEK
    -0.06
    POSITIVE LOGITS
    editable
    0.08
    醍
    0.07
    elib
    0.07
    wał
    0.06
     تمام
    0.06
    eren
    0.06
    ᴘ
    0.06
    娜
    0.06
    ábado
    0.06
    吁
    0.06
    Act Density 0.007%

    No Known Activations