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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    AVIS
    -0.07
    可靠性
    -0.07
     cheeks
    -0.07
    췃
    -0.07
    quiring
    -0.07
    🅚
    -0.06
    fans
    -0.06
     개인정보
    -0.06
    Mind
    -0.06
    碰
    -0.06
    POSITIVE LOGITS
    OO
    0.07
    ি
    0.07
     nhiệt
    0.07
     OF
    0.07
     `/
    0.07
     aç
    0.07
     скор
    0.07
    ọ
    0.07
     каж
    0.07
     하
    0.07
    Act Density 0.047%

    No Known Activations