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

    Neuronpedia

    INDEX
    Explanations

    capable

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ing
    -0.88
     capable
    -0.80
    was
    -0.65
    worthy
    -0.65
     rated
    -0.64
    seamnă
    -0.62
     itſelf
    -0.61
     épreuves
    -0.60
     Monfieur
    -0.58
     digna
    -0.57
    POSITIVE LOGITS
    TestingModule
    0.72
    DebuggerStep
    0.71
    setVerticalGroup
    0.69
     '\\;'
    0.68
    ChildScrollView
    0.65
     الرياضيه
    0.64
    ModelSerializer
    0.64
     des
    0.60
     EconPapers
    0.60
    )"),
    0.60
    Act Density 0.105%

    No Known Activations