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
    leo
    -0.07
    ريب
    -0.07
     tijd
    -0.06
    unde
    -0.06
    ILD
    -0.06
    주세요
    -0.06
     موس
    -0.06
     Brom
    -0.06
     Ont
    -0.06
     су
    -0.06
    POSITIVE LOGITS
    flags
    0.07
    _indent
    0.07
    -graph
    0.06
    Dig
    0.06
    <Props
    0.06
     такие
    0.06
     第三
    0.06
    @Repository
    0.06
    ,SLOT
    0.06
     Stall
    0.06
    Act Density 0.078%

    No Known Activations