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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     envelope
    -0.07
    iative
    -0.07
    map
    -0.07
    escription
    -0.06
     printf
    -0.06
     resumed
    -0.06
    nton
    -0.06
    丁目
    -0.06
    ивает
    -0.06
     Field
    -0.06
    POSITIVE LOGITS
    .instructions
    0.07
     معروف
    0.06
     trung
    0.06
    craper
    0.06
    itted
    0.06
     FIXED
    0.06
     Shooter
    0.06
     مقاله
    0.06
    half
    0.06
    ICI
    0.06
    Act Density 0.017%

    No Known Activations