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

    Neuronpedia

    INDEX
    Explanations

    missing

    np_max-act · gemini-2.0-flash

    This neuron activates on the word “missing,” flagging mentions of missing information.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Ao
    -0.07
     au
    -0.07
    チェ
    -0.07
    ALLE
    -0.06
     oct
    -0.06
     beh
    -0.06
     fe
    -0.06
    ाइड
    -0.06
     cud
    -0.06
     Hour
    -0.06
    POSITIVE LOGITS
     missing
    0.16
     Missing
    0.12
    Missing
    0.11
    _missing
    0.09
    missing
    0.07
     未
    0.07
     defective
    0.07
     MISSING
    0.07
    ्ग
    0.07
    贵
    0.07
    Act Density 0.007%

    No Known Activations