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

    Neuronpedia

    INDEX
    Explanations

    the

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ########.
    -0.45
    randrange
    -0.42
     LUMP
    -0.41
    AnimationsModule
    -0.40
    ckeditor
    -0.40
    reducers
    -0.40
    netti
    -0.40
    tagens
    -0.39
    Erstellt
    -0.39
     soldati
    -0.39
    POSITIVE LOGITS
     case
    0.90
     للمعارف
    0.68
    case
    0.66
    InjectAttribute
    0.62
     Case
    0.60
     system
    0.60
     geval
    0.60
    contentLoaded
    0.60
    bove
    0.58
     currentValue
    0.58
    Act Density 0.023%

    No Known Activations