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

    Neuronpedia

    INDEX
    Explanations

    work

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     funds
    -0.07
    퓪
    -0.07
    פורסם
    -0.07
    还有一些
    -0.07
     sexe
    -0.07
    Proxy
    -0.07
    SetColor
    -0.07
    评定
    -0.07
    Passwords
    -0.07
    躔
    -0.06
    POSITIVE LOGITS
    🧚
    0.07
    airobi
    0.07
     attic
    0.07
    PEAT
    0.06
    aling
    0.06
    'H
    0.06
    💁
    0.06
    italic
    0.06
    isable
    0.06
    .Rem
    0.06
    Act Density 0.011%

    No Known Activations