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

    Neuronpedia

    INDEX
    Explanations

    review scores

    np_max-act · gemini-2.0-flash

    This neuron never fires—it doesn’t detect any pattern in the text (i.e. it’s effectively “dead”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    acid
    -0.06
     Strip
    -0.06
     عبدال
    -0.06
     imperial
    -0.06
     dictated
    -0.06
    .counter
    -0.06
    _non
    -0.06
    "',
    -0.06
    _AUD
    -0.06
     Lua
    -0.06
    POSITIVE LOGITS
     qualitative
    0.06
     forecast
    0.06
     TODO
    0.06
    107
    0.06
     europé
    0.06
     změn
    0.06
     специалист
    0.06
    940
    0.06
    LIST
    0.06
     イ
    0.06
    Act Density 0.004%

    No Known Activations