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

    Neuronpedia

    INDEX
    Explanations

    map

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _bundle
    -0.07
    ést
    -0.06
     refl
    -0.06
    _Timer
    -0.06
    �
    -0.06
    Es
    -0.06
    开工建设
    -0.06
    انتخاب
    -0.06
     să
    -0.06
     إطلاق
    -0.06
    POSITIVE LOGITS
    @yahoo
    0.07
     אתרים
    0.06
    mployee
    0.06
    (optional
    0.06
    そうで
    0.06
     myself
    0.06
    女儿
    0.06
    ByVersion
    0.06
     misogyn
    0.06
     שקיבל
    0.06
    Act Density 0.033%

    No Known Activations