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
    صفقة
    -0.08
     ',',
    -0.07
    ⇾
    -0.07
    ()"↵
    -0.06
     split
    -0.06
     działania
    -0.06
     تعالى
    -0.06
     וגם
    -0.06
    ⌟
    -0.06
    DCALL
    -0.06
    POSITIVE LOGITS
     Vanessa
    0.08
    assets
    0.07
    鸟
    0.07
    _success
    0.07
    会让你
    0.07
    .ob
    0.07
    王晓
    0.07
    依靠
    0.07
    _ur
    0.06
     Merkel
    0.06
    Act Density 0.001%

    No Known Activations