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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash

    This neuron responds to short alphanumeric identifiers containing digits separated by hyphens (e.g. “L 1-1-05”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Ce
    -0.07
    site
    -0.07
    cers
    -0.06
     _)
    -0.06
    paypal
    -0.06
    /map
    -0.06
    ska
    -0.06
     zoals
    -0.06
     цій
    -0.06
     якій
    -0.06
    POSITIVE LOGITS
    )];
↵
    0.07
     Ravens
    0.06
    (CONFIG
    0.06
     starving
    0.06
    เศ
    0.06
     bloss
    0.06
     ros
    0.06
     Intelligent
    0.06
     newPos
    0.06
    ")]
↵
    0.06
    Act Density 0.043%

    No Known Activations