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
     freebies
    -0.07
    ర్ల
    -0.07
    arlos
    -0.07
    니다
    -0.07
     gemaakt
    -0.07
     FREE
    -0.07
    arren
    -0.07
    "↵↵
    -0.07
     niez
    -0.07
     hv
    -0.07
    POSITIVE LOGITS
     beispielsweise
    0.10
    مث
    0.10
    例えば
    0.09
     například
    0.09
     Miguel
    0.08
     bijvoorbeeld
    0.08
     Québec
    0.08
     reportedly
    0.08
     suddenly
    0.08
     diabet
    0.08
    Act Density 0.081%

    No Known Activations