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

    Neuronpedia

    INDEX
    Explanations

    say "For"

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    NavigationView
    -0.07
     году
    -0.07
    厂
    -0.07
    (robot
    -0.07
    лав
    -0.07
    从
    -0.07
     Scriptures
    -0.07
    ecs
    -0.06
     Redemption
    -0.06
    imizeBox
    -0.06
    POSITIVE LOGITS
     prostitution
    0.06
     Pare
    0.06
     inertia
    0.06
     Pent
    0.06
    †
    0.06
     보호
    0.06
     กรก
    0.06
     impro
    0.06
     gay
    0.06
    Pr
    0.06
    Act Density 0.006%

    No Known Activations