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

    Neuronpedia

    INDEX
    Explanations

    manufacturing

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    赜
    -0.08
    itary
    -0.07
    뵙
    -0.07
    畀
    -0.07
    枣庄
    -0.07
    贵金属
    -0.06
    ᆻ
    -0.06
    情报
    -0.06
    ():↵↵
    -0.06
    ";↵↵↵
    -0.06
    POSITIVE LOGITS
    IGNAL
    0.07
    inputEmail
    0.07
    prec
    0.07
    تد
    0.07
    Adventure
    0.07
    owania
    0.07
    ctrl
    0.07
     styl
    0.07
    pha
    0.07
    inn
    0.06
    Act Density 0.046%

    No Known Activations