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

    Neuronpedia

    INDEX
    Explanations

    numerical values and their relationships in data

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

    section numbers

    np_acts-logits-general · gemini-2.0-flash

    18 followed by punctuation or units

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    AnchorTagHelper
    -0.93
    ########.
    -0.92
     Waray
    -0.83
    tagHelperRunner
    -0.80
    izr
    -0.77
     CYTHON
    -0.74
    SourceChecksum
    -0.73
    setVerticalGroup
    -0.72
    CodedInputStream
    -0.72
    cookieParser
    -0.72
    POSITIVE LOGITS
     défend
    0.57
     useNavigate
    0.57
     SAGE
    0.55
     défendre
    0.52
    ñora
    0.51
     Aras
    0.50
     useHistory
    0.50
    tım
    0.50
     TNA
    0.49
     oxalate
    0.49
    Act Density 0.507%

    No Known Activations