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

    Neuronpedia

    INDEX
    Explanations

    deciding where to eat

    np_max-act · gemini-2.0-flash

    This neuron detects dialogue/speaker-turn language — tokens used in conversational turns, especially first- and second-person pronouns and speaker labels.

    oai_token-act-pair · gpt-5-miniTriggered by @yooniel31

    I

    np_max-act · gpt-5-miniTriggered by @yooniel31
    New Auto-Interp
    Negative Logits
    .;
    -0.08
     embraces
    -0.07
    according
    -0.07
    $template
    -0.07
     custody
    -0.07
    .Geometry
    -0.07
    ÔNG
    -0.07
     cuales
    -0.07
    According
    -0.06
    ENSOR
    -0.06
    POSITIVE LOGITS
    theid
    0.07
    álie
    0.06
    ungle
    0.06
     nerv
    0.06
    -prev
    0.06
    eking
    0.06
    rganization
    0.06
    asley
    0.06
    _First
    0.06
    earned
    0.06
    Act Density 0.107%

    No Known Activations