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

    Neuronpedia

    INDEX
    Explanations

    "do anything"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    zy
    -0.07
     ویرایش
    -0.07
    _log
    -0.06
     Gul
    -0.06
     months
    -0.06
    (factory
    -0.06
    (ins
    -0.06
    /part
    -0.06
    ,axis
    -0.06
     hrs
    -0.06
    POSITIVE LOGITS
     ejercicio
    0.07
     difficile
    0.06
     worked
    0.06
    ayette
    0.06
     husband
    0.06
    ayar
    0.06
     Sloven
    0.06
     امور
    0.06
     uterus
    0.06
     Guinness
    0.06
    Act Density 0.003%

    No Known Activations