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

    Neuronpedia

    INDEX
    Explanations

    each

    np_max-act · gemini-2.0-flash

    This neuron activates on instructional or directive prompts—imperative sentences that specify extracting or retrieving particular information.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    ̆
    -0.07
    .connection
    -0.07
     recipients
    -0.07
    �
    -0.06
    ('--
    -0.06
     CO
    -0.06
    Joy
    -0.06
    олет
    -0.06
    BEST
    -0.06
     Tavern
    -0.06
    POSITIVE LOGITS
    FontOfSize
    0.07
    .sorted
    0.07
     руку
    0.06
    ','=
    0.06
     cryptographic
    0.06
    :normal
    0.06
    _wait
    0.06
     Grammy
    0.06
     Keeper
    0.06
    _global
    0.06
    Act Density 0.088%

    No Known Activations