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

    Neuronpedia

    INDEX
    Explanations

    at

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    稹
    -0.08
    :image
    -0.07
     fathers
    -0.07
     Tulsa
    -0.07
    fontWeight
    -0.07
    gems
    -0.07
    moment
    -0.07
    🧙
    -0.07
    淡定
    -0.07
     rempl
    -0.07
    POSITIVE LOGITS
    iado
    0.07
     البي
    0.07
    ))]
    0.07
    информационн
    0.06
    (join
    0.06
    ificados
    0.06
     علي
    0.06
     zwłas
    0.06
     initWithNibName
    0.06
    受害
    0.06
    Act Density 0.003%

    No Known Activations