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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ipv
    -0.07
    сп
    -0.07
    cribes
    -0.07
    음을
    -0.06
     Nik
    -0.06
    іння
    -0.06
    Forgery
    -0.06
     역사
    -0.06
     ponto
    -0.06
    alış
    -0.06
    POSITIVE LOGITS
    腐
    0.06
    MAC
    0.06
    แบ
    0.06
    Ö
    0.06
    텔
    0.06
    BR
    0.06
    LEN
    0.06
     Jakarta
    0.06
    olicitud
    0.06
    (domain
    0.06
    Act Density 0.346%

    No Known Activations