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

    Neuronpedia

    INDEX
    Explanations

    resolution or regression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Ad
    -0.07
    "Oh
    -0.07
    FilePath
    -0.06
    破
    -0.06
    <P
    -0.06
    <F
    -0.06
     Belt
    -0.06
     billion
    -0.06
     oath
    -0.06
     props
    -0.06
    POSITIVE LOGITS
    (""))↵
    0.07
    сты
    0.07
    ذكر
    0.06
    viewModel
    0.06
     Teams
    0.06
    สอบ
    0.06
    ्टर
    0.06
     dim
    0.06
     commenter
    0.06
     commentator
    0.06
    Act Density 0.010%

    No Known Activations