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

    Neuronpedia

    INDEX
    Explanations

    of

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric expressions—particularly decimal numbers—within technical math passages.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     okul
    -0.06
     卡
    -0.06
     千
    -0.06
    yahoo
    -0.06
    senha
    -0.06
     сколько
    -0.06
    (sender
    -0.05
     Luz
    -0.05
     götür
    -0.05
     erased
    -0.05
    POSITIVE LOGITS
     contender
    0.07
    ło
    0.07
    elocity
    0.07
    Runner
    0.07
    .fasterxml
    0.07
    lauf
    0.07
     heir
    0.06
     wastes
    0.06
     была
    0.06
     gratuite
    0.06
    Act Density 0.041%

    No Known Activations