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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash

    This neuron fires on words signaling quickness or immediacy, such as “instant,” “almost instant,” and similar time-speed adverbs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     applaud
    -0.07
    291
    -0.06
    conf
    -0.06
     Nissan
    -0.06
     creed
    -0.06
     hostage
    -0.06
    ע
    -0.06
    trad
    -0.06
    .WEST
    -0.06
    trans
    -0.06
    POSITIVE LOGITS
     translate
    0.06
    Collections
    0.06
    )];
↵
    0.06
    prung
    0.06
    Module
    0.06
    ################################################################
    0.06
     etkisi
    0.06
     moderation
    0.06
     něj
    0.06
    .setFocus
    0.06
    Act Density 0.138%

    No Known Activations