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

    Neuronpedia

    INDEX
    Explanations

    Online forum/website snippets

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     anywhere
    -0.07
     günümüz
    -0.07
    مطلوب
    -0.07
     nederland
    -0.07
    俗称
    -0.07
    ıldığı
    -0.07
    رسم
    -0.07
    NotFoundError
    -0.07
     choisir
    -0.07
    _MATH
    -0.07
    POSITIVE LOGITS
    ess
    0.07
     siz
    0.07
     **/↵↵
    0.07
    Part
    0.07
    �
    0.07
    __),
    0.06
    '''
    0.06
    分辨
    0.06
    prim
    0.06
    >,
    0.06
    Act Density 0.213%

    No Known Activations