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
    usch
    -0.28
    èIJ½åľ°
    -0.27
    åĪ«çļĦ
    -0.26
     succesfully
    -0.26
    otp
    -0.25
    å¼Ĭ
    -0.25
    /pm
    -0.25
     Ruiz
    -0.24
    ouncing
    -0.24
    çļĦç¨ĭ度
    -0.24
    POSITIVE LOGITS
     historically
    0.31
     ancestry
    0.29
    dk
    0.28
    æѤæĸĩ
    0.28
    histor
    0.28
    .history
    0.27
    溯
    0.27
    eral
    0.27
    .Clock
    0.27
     Ah
    0.27
    Act Density 0.004%

    No Known Activations