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

    Neuronpedia

    INDEX
    Explanations

    Abbreviations with ampersands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     sce
    -0.07
     يجب
    -0.06
    nested
    -0.06
    getBlock
    -0.06
     curly
    -0.06
    ouse
    -0.06
    .relative
    -0.06
    BLOCK
    -0.06
     gim
    -0.06
    theon
    -0.06
    POSITIVE LOGITS
    áž
    0.07
    &R
    0.07
     (!$
    0.07
    溶
    0.07
    &D
    0.07
    Misc
    0.07
    &P
    0.06
    As
    0.06
    &w
    0.06
    <Image
    0.06
    Act Density 0.028%

    No Known Activations