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

    Neuronpedia

    INDEX
    Explanations

    programming-related terms and components

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

    Method and output formats

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    holt
    -0.43
    mobileqq
    -0.42
     محفوظة
    -0.41
    ftagPool
    -0.40
    ment
    -0.40
    НИК
    -0.40
    DrawerToggle
    -0.39
    optionalTypeArgs
    -0.39
    rent
    -0.37
    predicate
    -0.36
    POSITIVE LOGITS
    ſelves
    0.63
    IntoConstraints
    0.62
    +#+#
    0.60
    leſs
    0.59
    }*/
    0.58
    endphp
    0.57
    ſelf
    0.56
     leaſt
    0.55
     المعيارى
    0.55
     canst
    0.54
    Act Density 0.037%

    No Known Activations