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 mentions of multi-protein “complexes” (especially Polycomb repressive complexes and their subunits).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    -pane
    -0.07
     авг
    -0.07
     Sham
    -0.07
     acquaint
    -0.07
    月
    -0.07
     awakened
    -0.06
     satisfying
    -0.06
     तत
    -0.06
     simulation
    -0.06
    list
    -0.06
    POSITIVE LOGITS
     iş
    0.06
    uppy
    0.06
    __:
    0.06
     hüc
    0.06
    cím
    0.06
    uplic
    0.06
     Enabled
    0.06
     Tesla
    0.06
     coral
    0.06
    (Class
    0.06
    Act Density 0.019%

    No Known Activations