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

    Neuronpedia

    INDEX
    Explanations

    scientific technical descriptions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    iado
    -0.07
    _null
    -0.07
    Profit
    -0.07
     cliffs
    -0.07
     음
    -0.07
    _COUNTRY
    -0.06
    \View
    -0.06
     debugging
    -0.06
    /item
    -0.06
    严
    -0.06
    POSITIVE LOGITS
     decidedly
    0.07
    Really
    0.06
    ону
    0.06
     شور
    0.06
     scarc
    0.06
     Cz
    0.06
     Eugene
    0.06
    忽
    0.06
     सच
    0.06
     вариант
    0.06
    Act Density 0.059%

    No Known Activations