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

    Neuronpedia

    INDEX
    Explanations

    data excerpts

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    经济损失
    -0.08
    uy
    -0.07
    𝘢
    -0.07
    ений
    -0.07
    .food
    -0.07
    _barang
    -0.07
    סטי
    -0.07
    费用
    -0.07
    网络
    -0.07
    альный
    -0.07
    POSITIVE LOGITS
    habit
    0.07
    ɝ
    0.07
     Рус
    0.06
     imped
    0.06
    出会
    0.06
    AAF
    0.06
    intersect
    0.06
     impass
    0.06
    (alert
    0.06
     verb
    0.06
    Act Density 0.439%

    No Known Activations