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

    Neuronpedia

    INDEX
    Explanations

    mixture

    np_max-act · gemini-2.0-flash

    The neuron activates on terminology related to statistical mixture modeling (e.g. “mixture,” “model,” “EM,” “GMM”), so it’s essentially spotting references to mixture-model analyses.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    نج
    -0.07
    STYLE
    -0.06
     berlin
    -0.06
    Shown
    -0.06
     earlier
    -0.06
     visited
    -0.06
    JOB
    -0.06
     dictator
    -0.06
     feats
    -0.06
    ١
    -0.06
    POSITIVE LOGITS
    -inflammatory
    0.06
     Christina
    0.06
    ategoria
    0.06
    getic
    0.06
     SM
    0.06
     Provide
    0.06
     Consumer
    0.06
     compensation
    0.06
    박
    0.06
     прим
    0.06
    Act Density 0.003%

    No Known Activations