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

    Neuronpedia

    INDEX
    Explanations

    complex

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “complex” (including its form “complexified”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     exclusion
    -0.07
     Rif
    -0.07
    htm
    -0.06
    adem
    -0.06
    xfe
    -0.06
    _nv
    -0.06
     vote
    -0.06
    بدأ
    -0.06
     erken
    -0.06
    ेवल
    -0.06
    POSITIVE LOGITS
    Complex
    0.08
     complex
    0.07
     Complex
    0.07
    licate
    0.07
    mlx
    0.07
     stalls
    0.07
     Comes
    0.06
    ess
    0.06
     canlı
    0.06
     अच
    0.06
    Act Density 0.003%

    No Known Activations