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

    Neuronpedia

    INDEX
    Explanations

    example texts

    np_max-act · gemini-2.0-flash

    The neuron fires on the verb “say” in imperative prompts.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    _CLAMP
    -0.06
    stashop
    -0.06
     alloys
    -0.06
    cale
    -0.06
     ";"
    -0.06
    γι
    -0.06
     port
    -0.06
     キ
    -0.06
    iten
    -0.06
     drawn
    -0.06
    POSITIVE LOGITS
    sess
    0.06
    .Ret
    0.06
    ************************
    0.06
    ZIP
    0.06
     ann
    0.06
     seper
    0.06
    ๕
    0.06
    .Level
    0.06
    \Dependency
    0.06
     dumpster
    0.06
    Act Density 0.003%

    No Known Activations