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

    Neuronpedia

    INDEX
    Explanations

    code punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     manipulated
    -0.06
     genome
    -0.06
     tit
    -0.06
     purified
    -0.06
     beers
    -0.06
    aset
    -0.06
     Uniform
    -0.05
    재
    -0.05
    hv
    -0.05
     dal
    -0.05
    POSITIVE LOGITS
    Neutral
    0.07
    );}↵
    0.07
    ↵                    ↵
    0.07
    (...)↵
    0.07
    기업
    0.06
     Workshop
    0.06
    ↵        
↵
    0.06
    ">-->↵
    0.06
    .moveToFirst
    0.06
    CCI
    0.06
    Act Density 0.048%

    No Known Activations