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

    Neuronpedia

    INDEX
    Explanations

    Quotation mark

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    สำห
    -0.07
    _dropout
    -0.07
    PASSWORD
    -0.07
    辂
    -0.07
     press
    -0.07
    뽀
    -0.07
    늠
    -0.06
    )data
    -0.06
    榄
    -0.06
    /load
    -0.06
    POSITIVE LOGITS
    Restr
    0.09
    objet
    0.08
    ronic
    0.07
    keletal
    0.07
    (Font
    0.07
    (Device
    0.07
     cylindrical
    0.07
     الآن
    0.07
    📱
    0.07
     whistlebl
    0.07
    Act Density 0.000%

    No Known Activations