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

    Neuronpedia

    INDEX
    Explanations

    return

    np_max-act · gemini-2.0-flash

    This neuron is effectively dead—it never activates on any token.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    }};↵
    -0.08
    ].
    -0.07
     relig
    -0.07
     dossier
    -0.07
    edeyse
    -0.07
    ！
    -0.07
    expression
    -0.07
    urlpatterns
    -0.07
     ].
    -0.06
    bridge
    -0.06
    POSITIVE LOGITS
    管
    0.07
    orex
    0.06
    отов
    0.06
    eder
    0.06
     pueden
    0.06
     tá
    0.06
     timeouts
    0.06
    Ré
    0.06
    (dr
    0.06
     grabbed
    0.06
    Act Density 0.019%

    No Known Activations