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

    Neuronpedia

    INDEX
    Explanations

    Technical/academic processes

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     בהם
    -0.07
     Upload
    -0.06
    acji
    -0.06
    'à
    -0.06
     Dresden
    -0.06
     dóla
    -0.06
     może
    -0.06
     destructive
    -0.06
    ności
    -0.06
    新春
    -0.06
    POSITIVE LOGITS
    我家
    0.07
     fileSize
    0.07
     kappa
    0.07
     implementation
    0.07
     condem
    0.07
    UCCEEDED
    0.07
    用户的
    0.07
     coff
    0.06
    getSource
    0.06
     관심
    0.06
    Act Density 0.101%

    No Known Activations