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

    Neuronpedia

    INDEX
    Explanations

    feature

    np_max-act · gemini-2.0-flash

    This neuron responds to the appearance of the verb “features” (and its close variants) in descriptive sentences.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     clamp
    -0.07
     ANSW
    -0.07
     global
    -0.07
    (zip
    -0.07
     yyn
    -0.06
     bind
    -0.06
     takes
    -0.06
     suppress
    -0.06
     giveaways
    -0.06
     escape
    -0.06
    POSITIVE LOGITS
     featuring
    0.10
     features
    0.08
     Featuring
    0.07
    aysia
    0.07
    porto
    0.07
    uest
    0.07
     �
    0.07
    stein
    0.06
     perfection
    0.06
     Features
    0.06
    Act Density 0.012%

    No Known Activations