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

    Neuronpedia

    INDEX
    Explanations

    pronouns

    np_max-act · gemini-2.0-flash

    The neuron lights up on content words denoting actions—i.e. verbs.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    する
    -0.07
     قرارد
    -0.07
    幹
    -0.07
    Metadata
    -0.06
    --,
    -0.06
    })↵↵↵
    -0.06
    .simps
    -0.06
     breeds
    -0.06
     dashes
    -0.06
     signatures
    -0.06
    POSITIVE LOGITS
     mientras
    0.07
    bett
    0.07
    0.07
    DU
    0.07
     paralle
    0.07
    getting
    0.07
    we
    0.07
     WF
    0.06
     issu
    0.06
     �
    0.06
    Act Density 0.037%

    No Known Activations