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

    Neuronpedia

    INDEX
    Explanations

    description

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     United
    -0.08
     Banc
    -0.07
     pytest
    -0.07
     CART
    -0.06
     Details
    -0.06
     Hz
    -0.06
    吊
    -0.06
     Re
    -0.06
    臧
    -0.06
     Phen
    -0.06
    POSITIVE LOGITS
    ทหาร
    0.07
    一群人
    0.07
     pornofil
    0.07
     Projectile
    0.07
    .Instance
    0.07
    #undef
    0.07
    𝇚
    0.07
    olicies
    0.07
     prostitutes
    0.07
     gente
    0.07
    Act Density 0.048%

    No Known Activations