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
    ющую
    -0.07
    álie
    -0.06
    bh
    -0.06
    acf
    -0.06
    SetValue
    -0.06
     Regarding
    -0.06
    Cleaning
    -0.06
    ()}
    -0.06
     Disease
    -0.06
    Regex
    -0.06
    POSITIVE LOGITS
    ่าจะ
    0.09
     monoc
    0.07
    ISIBLE
    0.07
     boats
    0.07
    NOT
    0.06
     vlak
    0.06
    brakk
    0.06
     ناب
    0.06
     Guth
    0.06
    ียร
    0.06
    Act Density 0.009%

    No Known Activations