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

    Neuronpedia

    INDEX
    Explanations

    programming

    np_max-act · gemini-2.0-flash

    This neuron lights up on key data‐structure or data‐type terms in programming prompts—words like “string,” “file,” “maps,” and “objects.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     premi
    -0.07
    _cam
    -0.07
    (chan
    -0.06
    私の
    -0.06
    has
    -0.06
    331
    -0.06
    ثال
    -0.06
    pleasant
    -0.06
    to
    -0.06
    arming
    -0.06
    POSITIVE LOGITS
    ングル
    0.07
     توس
    0.07
     queryString
    0.06
    opyright
    0.06
     duplicated
    0.06
    [input
    0.06
     Sentinel
    0.06
    .Generated
    0.06
     Management
    0.06
    -management
    0.06
    Act Density 0.098%

    No Known Activations