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

    Neuronpedia

    INDEX
    Explanations

    fix

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ंदीखरीदारी
    -0.65
     estekak
    -0.56
     muualla
    -0.54
    MLLoader
    -0.52
    isteren
    -0.50
    TypedDataSet
    -0.49
    yarnpkg
    -0.49
    minecraft
    -0.47
    ziplin
    -0.47
    onomía
    -0.46
    POSITIVE LOGITS
     typos
    0.81
     up
    0.72
     mistakes
    0.65
    up
    0.64
    MethodManager
    0.61
     errors
    0.61
     Up
    0.59
    TagHelper
    0.58
     agrí
    0.57
    EndInit
    0.57
    Act Density 0.009%

    No Known Activations