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

    Neuronpedia

    INDEX
    Explanations

    bull

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     ao
    -0.07
    REC
    -0.07
     &&
    -0.06
     aos
    -0.06
    >s
    -0.06
     Symbol
    -0.06
    ăng
    -0.06
     доч
    -0.06
     ss
    -0.06
    Token
    -0.06
    POSITIVE LOGITS
     Bulletin
    0.09
     Bull
    0.08
    bul
    0.08
    bull
    0.08
     bull
    0.08
    uckles
    0.07
    Bulletin
    0.07
     Bul
    0.07
     bully
    0.07
     bullying
    0.07
    Act Density 0.014%

    No Known Activations