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

    Neuronpedia

    INDEX
    Explanations

    Articles/Publications

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    اين
    -0.07
    ulence
    -0.07
     Marvel
    -0.06
    71
    -0.06
    ffffff
    -0.06
     BRAND
    -0.06
     mad
    -0.06
    .jd
    -0.06
     joke
    -0.06
    type
    -0.06
    POSITIVE LOGITS
     -->
↵
    0.07
    ILog
    0.07
     yasal
    0.07
     enquanto
    0.07
    .setData
    0.06
     france
    0.06
     mí
    0.06
     unreliable
    0.06
    Configurer
    0.06
    опри
    0.06
    Act Density 0.004%

    No Known Activations