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

    Neuronpedia

    INDEX
    Explanations

    install

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Clothing
    -0.08
    �
    -0.07
     ydk
    -0.07
     Phy
    -0.07
    ?(
    -0.07
    と言
    -0.07
    Blood
    -0.07
    碴
    -0.07
     Democr
    -0.07
    �
    -0.07
    POSITIVE LOGITS
     Winners
    0.06
     helper
    0.06
    ammers
    0.06
    poons
    0.06
     mktime
    0.06
     الزوج
    0.06
    coles
    0.06
    蒎
    0.06
    웢
    0.06
    ktor
    0.06
    Act Density 0.009%

    No Known Activations