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

    Neuronpedia

    INDEX
    Explanations

    Assembling

    np_max-act · gemini-2.0-flash

    This neuron detects phrases that describe assembling or putting something together (e.g. “put together,” “montar uma”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     watershed
    -0.07
     người
    -0.06
    需要
    -0.06
     افزایش
    -0.06
    ’deki
    -0.06
     aantal
    -0.06
     xrange
    -0.06
    郡
    -0.06
    _rank
    -0.06
     caused
    -0.06
    POSITIVE LOGITS
     assemble
    0.11
     assembling
    0.10
     assembled
    0.08
    semble
    0.08
    编
    0.08
    -formed
    0.07
    _COMPONENT
    0.07
    .wik
    0.07
     subscribe
    0.07
    builder
    0.07
    Act Density 0.041%

    No Known Activations