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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to legal statutes and consequences

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

    "18" followed by a unit of time

    np_acts-logits-general · gemini-2.0-flash

    numbers with 8

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ########.
    -0.86
    tagHelperRunner
    -0.85
    MLLoader
    -0.81
     surla
    -0.79
    izr
    -0.78
     Waray
    -0.77
    AnchorTagHelper
    -0.77
    SourceChecksum
    -0.76
    HasForeignKey
    -0.73
     CYTHON
    -0.71
    POSITIVE LOGITS
     SAGE
    0.63
     xóa
    0.56
    thme
    0.56
     useNavigate
    0.54
    tım
    0.53
     défend
    0.53
    Ведь
    0.52
     useHistory
    0.52
    zeß
    0.52
    FINISH
    0.52
    Act Density 0.570%

    No Known Activations