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

    Neuronpedia

    INDEX
    Explanations

    say

    np_max-act · gemini-2.0-flash

    The neuron primarily activates on the imperative verb “say.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     ге
    -0.07
    」の
    -0.07
    基地
    -0.06
    )':
    -0.06
     diffs
    -0.06
    ُو
    -0.06
    ”),
    -0.06
    ;",
    -0.06
    ")),
    -0.06
     tsl
    -0.06
    POSITIVE LOGITS
     Hayes
    0.07
    सत
    0.07
     Proper
    0.07
     variety
    0.07
    leneck
    0.07
     Scale
    0.06
     ح
    0.06
    観
    0.06
    ads
    0.06
    continued
    0.06
    Act Density 0.003%

    No Known Activations