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

    Neuronpedia

    INDEX
    Explanations

    lines of code or coding-related references

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

    programming code references

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    SpringRunner
    -0.47
    xnn
    -0.45
    WaitGroup
    -0.43
    __*/
    -0.42
     (!__
    -0.42
    (||
    -0.40
     zufolge
    -0.39
    ArgsConstructor
    -0.38
    duras
    -0.38
    .)}
    -0.38
    POSITIVE LOGITS
     code
    1.09
     Code
    1.08
    code
    1.02
    Code
    0.98
     CODE
    0.91
     setCode
    0.88
    setCode
    0.88
    getCode
    0.82
     getCode
    0.78
     Codes
    0.77
    Act Density 0.034%

    No Known Activations