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

    Neuronpedia

    INDEX
    Explanations

    factor

    np_max-act · gemini-2.0-flash

    The neuron detects terms that indicate arithmetic divisibility or factor/multiple relationships (e.g. “divide,” “factor,” “multiple”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _yellow
    -0.07
    Consult
    -0.07
     Characters
    -0.07
     philippines
    -0.06
    -services
    -0.06
    ดง
    -0.06
    position
    -0.06
     tele
    -0.06
    riends
    -0.06
     Leading
    -0.06
    POSITIVE LOGITS
    /custom
    0.07
     ağ
    0.07
    (sc
    0.07
     partes
    0.07
     GE
    0.07
    λευ
    0.06
     jug
    0.06
     diagn
    0.06
    .algorithm
    0.06
     plugin
    0.06
    Act Density 0.002%

    No Known Activations