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
     thổ
    -0.06
     votes
    -0.06
     withdrew
    -0.06
     dashed
    -0.06
    =params
    -0.06
    унк
    -0.06
    ❤
    -0.06
     surprise
    -0.06
     Brief
    -0.06
    vasive
    -0.06
    POSITIVE LOGITS
     조선
    0.07
    เย
    0.07
     cred
    0.06
    akhstan
    0.06
    chrift
    0.06
     helium
    0.06
    搜
    0.06
    věd
    0.06
    ládání
    0.06
     Millionen
    0.06
    Act Density 0.039%

    No Known Activations