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

    Neuronpedia

    INDEX
    Explanations

    surprising events

    np_max-act · gemini-2.0-flash

    The neuron detects idiomatic “it’s no … that …” or “it’s not/never …” discourse frames that present information as unsurprising or obvious.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    امه
    -0.07
    از
    -0.06
    IfExists
    -0.06
    .ld
    -0.06
    йн
    -0.06
     perennial
    -0.06
     Workbook
    -0.06
    ITED
    -0.06
    AMPLE
    -0.06
     رم
    -0.06
    POSITIVE LOGITS
     shortest
    0.07
     trying
    0.06
     lost
    0.06
     aerospace
    0.06
    "No
    0.06
    ině
    0.06
     skip
    0.06
    -na
    0.06
    _SUCCESS
    0.06
    .Man
    0.06
    Act Density 0.053%

    No Known Activations