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

    Neuronpedia

    INDEX
    Explanations

    reduction

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of mechanical speed-reduction components—e.g. “reduction,” “gear,” “gearhead,” “planetary gear,” etc.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    +x
    -0.07
     distinction
    -0.07
    ,eg
    -0.07
     tup
    -0.06
     Digest
    -0.06
     vault
    -0.06
     Moist
    -0.06
    .Addr
    -0.06
     trot
    -0.06
     x
    -0.06
    POSITIVE LOGITS
    ели
    0.07
     natuur
    0.07
    arena
    0.06
    ева
    0.06
     belirli
    0.06
    _blk
    0.06
    инов
    0.06
     громадян
    0.06
    ımı
    0.06
    Words
    0.06
    Act Density 0.007%

    No Known Activations