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

    Neuronpedia

    INDEX
    Explanations

    _table

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     simplistic
    -0.07
    -rating
    -0.06
    [$_
    -0.06
     DESCRIPTION
    -0.06
     أق
    -0.06
     impressive
    -0.06
    _Function
    -0.06
    lates
    -0.06
    annies
    -0.06
     lion
    -0.06
    POSITIVE LOGITS
    обы
    0.07
    дин
    0.06
    Ѕ
    0.06
     instruction
    0.06
    　ヾ
    0.06
    道路
    0.06
     Ens
    0.06
    ธรรม
    0.06
    _LIST
    0.06
     anatomy
    0.06
    Act Density 0.000%

    No Known Activations