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

    Neuronpedia

    INDEX
    Explanations

    coding advice

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _BACKEND
    -0.06
    ходить
    -0.06
     Modules
    -0.06
    �
    -0.06
    Na
    -0.06
    cházet
    -0.06
    .info
    -0.06
    、この
    -0.06
    оны
    -0.06
    URAL
    -0.06
    POSITIVE LOGITS
    ctype
    0.07
    antidad
    0.06
    ECT
    0.06
    äm
    0.06
     alanı
    0.06
    toggle
    0.06
     Athletic
    0.06
     fluct
    0.06
     txt
    0.06
    _lr
    0.06
    Act Density 0.016%

    No Known Activations