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

    Neuronpedia

    INDEX
    Explanations

    code diagrams

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Marriage
    -0.07
    =random
    -0.06
     sexual
    -0.06
    =@
    -0.06
    MMMM
    -0.06
    itution
    -0.06
     Critical
    -0.06
    ізнес
    -0.06
     ماه
    -0.06
    епти
    -0.06
    POSITIVE LOGITS
    TCHA
    0.07
     disrupt
    0.07
    rots
    0.07
    уск
    0.06
     grues
    0.06
    voj
    0.06
     filtering
    0.06
    SPI
    0.06
    <Void
    0.06
     frac
    0.06
    Act Density 0.004%

    No Known Activations