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

    Neuronpedia

    INDEX
    Explanations

    from

    np_max-act · gemini-2.0-flash

    This neuron never activates on any of the shown tokens—it doesn’t detect any pattern (i.e. it’s effectively “dead” on this data).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    Adjust
    -0.07
     Opr
    -0.06
    Op
    -0.06
    _j
    -0.06
    hp
    -0.06
    clado
    -0.06
    11
    -0.06
    serial
    -0.06
     stud
    -0.06
     keynote
    -0.05
    POSITIVE LOGITS
     inaccessible
    0.08
    essim
    0.07
     열
    0.07
    ΠΑ
    0.07
     امروز
    0.07
     popcorn
    0.07
     사항
    0.07
    หา
    0.07
    rang
    0.07
    ounce
    0.07
    Act Density 0.011%

    No Known Activations