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

    Neuronpedia

    INDEX
    Explanations

    numerical values related to time, age, and measurements

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

    numbers, ranges, and comparisons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     je
    -0.38
     cork
    -0.37
     fair
    -0.37
     mili
    -0.37
     ✭✭
    -0.36
     Schatz
    -0.35
    ValueStyle
    -0.35
     Seven
    -0.35
     partnering
    -0.34
     phong
    -0.34
    POSITIVE LOGITS
    WriteTagHelper
    0.73
     AssemblyCulture
    0.66
     surla
    0.65
    ArgsConstructor
    0.57
     defaultstate
    0.56
     Efq
    0.56
     myſelf
    0.55
     الحره
    0.55
    TokenNameLPAREN
    0.55
     raiſ
    0.54
    Act Density 0.049%

    No Known Activations