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

    Neuronpedia

    INDEX
    Explanations

    Hello

    np_max-act · gemini-2.0-flash

    This neuron fires on literal string content inside quotation marks (e.g., the “Hello, World!” tokens).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     received
    -0.07
     doses
    -0.07
     fix
    -0.07
    _keyword
    -0.06
     medals
    -0.06
     night
    -0.06
     dress
    -0.06
    -third
    -0.06
     bad
    -0.06
     brib
    -0.06
    POSITIVE LOGITS
    DllImport
    0.07
     dalla
    0.07
    :");↵
    0.07
     skupiny
    0.06
    [DllImport
    0.06
    '>";↵
    0.06
    олод
    0.06
    olvency
    0.06
    ourcem
    0.06
    .isNotBlank
    0.06
    Act Density 0.012%

    No Known Activations