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
     Stellar
    -0.06
     Livingston
    -0.06
    ="<?=
    -0.06
     Wor
    -0.06
    ibur
    -0.06
     раніше
    -0.06
     Diaz
    -0.06
     Studi
    -0.06
    ivé
    -0.06
     McCl
    -0.06
    POSITIVE LOGITS
    _follow
    0.08
    ئيس
    0.07
    ISODE
    0.07
    -method
    0.07
     anticipated
    0.07
     aren
    0.07
     От
    0.06
    实
    0.06
    و
    0.06
    /";↵
    0.06
    Act Density 0.043%

    No Known Activations