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

    Neuronpedia

    INDEX
    Explanations

    Delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     stood
    -0.08
     شهر
    -0.07
    _system
    -0.07
     domicile
    -0.07
    _my
    -0.07
    BREAK
    -0.07
    Mis
    -0.07
     cont
    -0.07
    byn
    -0.07
    热门
    -0.06
    POSITIVE LOGITS
    𝙥
    0.07
     awful
    0.07
    enzhen
    0.07
    回头
    0.06
     Ohio
    0.06
    奭
    0.06
     وقد
    0.06
    苈
    0.06
    ;'>
    0.06
    _delay
    0.06
    Act Density 0.015%

    No Known Activations