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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Towers
    -0.07
     Rak
    -0.07
     Flem
    -0.07
     brand
    -0.07
    rysler
    -0.07
     张
    -0.06
    ีท
    -0.06
    Proc
    -0.06
     Hawks
    -0.06
    상을
    -0.06
    POSITIVE LOGITS
    "]];↵
    0.07
     disruptions
    0.07
    labilir
    0.06
    _R
    0.06
    žení
    0.06
     Published
    0.06
    .scalar
    0.06
    Started
    0.06
    -main
    0.06
    起来
    0.06
    Act Density 0.158%

    No Known Activations