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

    Neuronpedia

    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    �
    -0.07
    講
    -0.07
    Unauthorized
    -0.07
     palace
    -0.07
     všechno
    -0.06
    brief
    -0.06
    bak
    -0.06
     identify
    -0.06
    ragment
    -0.06
    "]=
    -0.06
    POSITIVE LOGITS
    ΗΝ
    0.07
    Entities
    0.06
     hisset
    0.06
     نیروی
    0.06
     dnů
    0.06
    elial
    0.06
    ("/{
    0.06
    irates
    0.06
    .disabled
    0.06
     française
    0.06
    Act Density 0.001%

    No Known Activations