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

    Neuronpedia

    INDEX
    Explanations

    assertions and testing-related terminology

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Assertions, especially those named "assert"

    np_acts-logits-general · gemini-2.0-flash

    assert receive or equal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DockStyle
    -0.68
     الاطلاع
    -0.60
    ginate
    -0.55
    ThemeOverlay
    -0.54
    IBinder
    -0.48
    Espèce
    -0.48
    VELAND
    -0.48
    hasiswa
    -0.47
    __':
    -0.47
    sidemargin
    -0.46
    POSITIVE LOGITS
     true
    0.68
     rằng
    0.68
     bahwa
    0.68
    True
    0.66
     equal
    0.65
    (!(
    0.64
    (!
    0.63
     !
    0.61
     True
    0.60
     Equal
    0.60
    Act Density 0.067%

    No Known Activations