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

    Neuronpedia

    INDEX
    Explanations

    Code/math formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Crop
    -0.07
     вважа
    -0.07
    人は
    -0.07
     republican
    -0.06
     documents
    -0.06
     bishops
    -0.06
    ьому
    -0.06
     oslo
    -0.06
     minha
    -0.06
     knife
    -0.06
    POSITIVE LOGITS
     \"%
    0.07
     JOB
    0.07
    animations
    0.07
    .getDay
    0.07
    idual
    0.06
    .SQLException
    0.06
     sint
    0.06
    ,String
    0.06
     merch
    0.06
     GestureDetector
    0.06
    Act Density 0.038%

    No Known Activations