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

    Neuronpedia

    INDEX
    Explanations

    locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    conde
    -0.07
    inicio
    -0.07
     Berlin
    -0.06
    _FATAL
    -0.06
    	Status
    -0.06
    naz
    -0.06
     guarante
    -0.06
    MP
    -0.06
    Servlet
    -0.06
    awy
    -0.06
    POSITIVE LOGITS
    ("$.
    0.06
     풀
    0.06
     bloginfo
    0.06
     εργ
    0.06
    /stat
    0.06
     polov
    0.06
    ‌شده
    0.06
     wors
    0.06
     Cody
    0.06
     onCancel
    0.06
    Act Density 0.032%

    No Known Activations