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

    Neuronpedia

    INDEX
    Explanations

    -body

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     nouns
    -0.07
    Persona
    -0.07
    ايش
    -0.06
    altar
    -0.06
    ู่
    -0.06
     полити
    -0.06
     Jed
    -0.06
    дом
    -0.06
    coupon
    -0.06
     prend
    -0.06
    POSITIVE LOGITS
    /result
    0.07
    -body
    0.07
     ал
    0.07
    Handle
    0.07
    .Errorf
    0.07
    Body
    0.06
    0.06
     bil
    0.06
    .r
    0.06
     captivating
    0.06
    Act Density 0.004%

    No Known Activations