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

    Neuronpedia

    INDEX
    Explanations

    coefficient

    np_max-act · gemini-2.0-flash

    This neuron activates on mentions of numeric “coefficient” (and related forms) in text.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    165
    -0.08
    Actualizar
    -0.07
     walk
    -0.07
    323
    -0.07
     PARK
    -0.07
    325
    -0.07
     armed
    -0.07
     park
    -0.07
    Mary
    -0.06
     uptime
    -0.06
    POSITIVE LOGITS
     coefficient
    0.12
     coefficients
    0.12
    Coefficient
    0.08
    efficient
    0.08
     Cohen
    0.08
    coeff
    0.08
    Coeff
    0.08
     Wheel
    0.07
     conquest
    0.07
     Coleman
    0.07
    Act Density 0.005%

    No Known Activations