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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash

    The neuron fires on camel-case identifier tokens (e.g. variable names like “redButton,” “maxButton,” “webView”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     detained
    -0.06
     polo
    -0.06
    "),↵↵
    -0.06
     segregation
    -0.06
    include
    -0.06
    Orientation
    -0.06
    _hero
    -0.06
    ورن
    -0.06
    .intro
    -0.06
    出来
    -0.05
    POSITIVE LOGITS
    "bytes
    0.07
    suma
    0.06
     Steak
    0.06
    闘
    0.06
     TSRMLS
    0.06
     justified
    0.06
     mistress
    0.06
    :o
    0.06
     implicit
    0.06
     Место
    0.06
    Act Density 0.013%

    No Known Activations