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

    Neuronpedia

    INDEX
    Explanations

    possibility

    np_max-act · gemini-2.0-flash

    This neuron never fires on any of the shown text—essentially it’s inactive (a “dead” neuron).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -red
    -0.07
    .feed
    -0.06
     양
    -0.06
     BUF
    -0.06
     광
    -0.06
    (second
    -0.06
     indir
    -0.06
     Wildlife
    -0.06
     slot
    -0.06
    ower
    -0.06
    POSITIVE LOGITS
    /bind
    0.07
     geral
    0.07
    details
    0.06
     nombres
    0.06
     بالإ
    0.06
     Province
    0.06
    テレビ
    0.06
     AABB
    0.06
    virtual
    0.06
     χρόνια
    0.06
    Act Density 0.115%

    No Known Activations