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

    Neuronpedia

    INDEX
    Explanations

    terminal output

    np_max-act · gemini-2.0-flash

    The neuron fires on the numeric parts (digits and brackets) of ANSI‐style terminal escape sequences (e.g. “\033[31m” etc.).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    อากาศ
    -0.07
    imating
    -0.07
    _qual
    -0.07
    population
    -0.07
    iversity
    -0.06
     blockers
    -0.06
    chrift
    -0.06
     ceremon
    -0.06
     LIB
    -0.06
    ond
    -0.06
    POSITIVE LOGITS
    FormattedMessage
    0.07
    stdbool
    0.06
    '));
↵
    0.06
    전에
    0.06
    JR
    0.06
     glaring
    0.06
    toBeTruthy
    0.06
    RIPTION
    0.06
    *******************************************************************************/↵
    0.06
    .Translate
    0.06
    Act Density 0.003%

    No Known Activations