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

    Neuronpedia

    INDEX
    Explanations

    technical information

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    誉
    -0.07
     sill
    -0.07
    -h
    -0.07
    /Application
    -0.07
    jia
    -0.07
    eki
    -0.07
     Gloria
    -0.07
     neglect
    -0.07
     rév
    -0.07
    nila
    -0.06
    POSITIVE LOGITS
     mögen
    0.08
    -loving
    0.08
     سيارة
    0.08
    лав
    0.08
     Wel
    0.08
     workplaces
    0.07
     بودن
    0.07
    Channels
    0.07
     بتوان
    0.07
     языке
    0.07
    Act Density 0.030%

    No Known Activations