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

    Neuronpedia

    INDEX
    Explanations

    abi

    np_max-act · gemini-2.0-flash

    The neuron fires on section‐heading words (like “Goals,” “Roles,” “Objectives,” etc.) that label key planning elements.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     bursts
    -0.07
     follic
    -0.07
    Theo
    -0.07
     intelligent
    -0.07
     Arn
    -0.07
     mixes
    -0.06
     genetics
    -0.06
    gps
    -0.06
     impacted
    -0.06
     impulse
    -0.06
    POSITIVE LOGITS
    �
    0.07
     знаю
    0.07
     *↵↵↵
    0.06
     mommy
    0.06
     seins
    0.06
    ('../
    0.06
    plusplus
    0.06
    (Position
    0.06
     "../
    0.06
     břez
    0.05
    Act Density 0.074%

    No Known Activations