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

    Neuronpedia

    INDEX
    Explanations

    YA

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Mad
    -0.07
    Mad
    -0.07
    Nh
    -0.06
    شنبه
    -0.06
     boiling
    -0.06
    рен
    -0.06
    oph
    -0.06
     Bite
    -0.06
     patio
    -0.06
     Requests
    -0.06
    POSITIVE LOGITS
     simply
    0.07
     पड़
    0.07
    ()},
    0.06
    斷
    0.06
     vur
    0.06
     LogLevel
    0.06
    -fin
    0.06
    weak
    0.06
     Panasonic
    0.06
    debug
    0.06
    Act Density 0.007%

    No Known Activations