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

    Neuronpedia

    INDEX
    Explanations

    equals sign

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Ɛ
    -0.07
    ;top
    -0.07
     Owens
    -0.07
     [--
    -0.07
     basil
    -0.06
     biên
    -0.06
    -carousel
    -0.06
    镰
    -0.06
     DAR
    -0.06
    frared
    -0.06
    POSITIVE LOGITS
     nhiều
    0.07
    _after
    0.07
    _patterns
    0.07
    تدريب
    0.06
     많은
    0.06
    룡
    0.06
     رائع
    0.06
    と言う
    0.06
     fraudulent
    0.06
     heartfelt
    0.06
    Act Density 0.000%

    No Known Activations