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

    Neuronpedia

    INDEX
    Explanations

    delay

    np_max-act · gemini-2.0-flash

    The main thing this neuron does is detect numeric tokens, especially decimal number fragments.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ambit
    -0.06
     않는
    -0.06
    Over
    -0.06
    vědom
    -0.06
     üzer
    -0.06
    eliminar
    -0.06
    (net
    -0.06
    ぅ
    -0.06
    _ATTACH
    -0.06
     เขต
    -0.06
    POSITIVE LOGITS
    _REQ
    0.07
    Greg
    0.07
     dsp
    0.07
     FORMAT
    0.07
     Investments
    0.07
    .String
    0.07
     delays
    0.06
     Ná
    0.06
    _manifest
    0.06
    summary
    0.06
    Act Density 0.013%

    No Known Activations