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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    abeth
    -0.07
    اپیم
    -0.07
    ases
    -0.07
    (disposing
    -0.07
     wich
    -0.07
    eros
    -0.06
    BuildContext
    -0.06
    AVIS
    -0.06
    ampton
    -0.06
     HOH
    -0.06
    POSITIVE LOGITS
     accessible
    0.07
     FG
    0.07
    něte
    0.06
    :utf
    0.06
    iband
    0.06
    __["
    0.06
     tacos
    0.06
     tất
    0.06
    >)↵
    0.06
     عامة
    0.06
    Act Density 0.010%

    No Known Activations