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

    Neuronpedia

    INDEX
    Explanations

    ARM

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Welfare
    -0.07
    Millis
    -0.06
     Gaz
    -0.06
     bao
    -0.06
    Predict
    -0.06
     neredeyse
    -0.06
     caliber
    -0.06
     wished
    -0.06
     Pub
    -0.06
    BoundingBox
    -0.06
    POSITIVE LOGITS
     ARM
    0.08
    ленні
    0.07
    лення
    0.06
    恩
    0.06
     err
    0.06
     opts
    0.06
    isValid
    0.06
    340
    0.06
    .arm
    0.06
     RedirectToAction
    0.06
    Act Density 0.001%

    No Known Activations