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
    EDEFAULT
    -0.56
    saraba
    -0.53
    viewDidLoad
    -0.52
    ьаж
    -0.50
    бки
    -0.48
    izi
    -0.47
     carelessness
    -0.47
     financiamiento
    -0.47
    afterEach
    -0.47
     Vern
    -0.47
    POSITIVE LOGITS
     typelib
    0.78
    MethodManager
    0.66
    CodedInputStream
    0.60
    RegistryLite
    0.59
     protoimpl
    0.57
     allows
    0.55
    TintMode
    0.54
     ComVisible
    0.52
     Audiodateien
    0.52
    ollectionView
    0.51
    Act Density 0.001%

    No Known Activations