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

    Neuronpedia

    INDEX
    Explanations

    Conversational anecdotes

    np_max-act · gemini-2.0-flash

    The neuron fires on first‐person experience statements indicating personal ownership or recommendation (e.g. “I have one and like it”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     Motorola
    -0.07
     Lady
    -0.07
     troubleshooting
    -0.07
    .Usuario
    -0.06
     blown
    -0.06
     Hungarian
    -0.06
     leaking
    -0.06
    ще
    -0.06
    ittest
    -0.06
     Leer
    -0.06
    POSITIVE LOGITS
     astounding
    0.07
    ґ
    0.06
    terraform
    0.06
    ...',
    0.06
     ال
    0.06
    StoryboardSegue
    0.06
    barang
    0.06
     Pel
    0.06
     ();
↵
    0.06
    －
    0.06
    Act Density 0.038%

    No Known Activations