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

    Neuronpedia

    INDEX
    Explanations

    universities and institutions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     إلي
    -0.07
     lam
    -0.07
    ǜ
    -0.07
    islation
    -0.07
     Vil
    -0.07
     Napoleon
    -0.07
    auf
    -0.07
     portrays
    -0.07
     posture
    -0.07
     uuid
    -0.07
    POSITIVE LOGITS
    _remote
    0.08
    \application
    0.07
    注销
    0.07
    댤
    0.07
    _marker
    0.07
    (logger
    0.06
    采用
    0.06
    てしまって
    0.06
    مصطف
    0.06
    ,res
    0.06
    Act Density 0.170%

    No Known Activations