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

    Neuronpedia

    INDEX
    Explanations

    ogenesis

    np_max-act · gemini-2.0-flash

    The neuron is sensitive to occurrences of the substring “ogenesis,” i.e. words ending in “-ogenesis.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     unfair
    -0.07
     Brown
    -0.06
     Royal
    -0.06
     fill
    -0.06
     trick
    -0.06
     honors
    -0.06
     즐
    -0.06
     Robert
    -0.06
     zw
    -0.06
     ranks
    -0.06
    POSITIVE LOGITS
    ogenesis
    0.12
    Genesis
    0.08
     genesis
    0.08
    गढ
    0.07
    genesis
    0.07
     것이
    0.07
    기에
    0.07
    -gallery
    0.07
    іння
    0.07
     Genesis
    0.07
    Act Density 0.005%

    No Known Activations