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

    Neuronpedia

    INDEX
    Explanations

    Describing insignificant experimental results

    np_max-act · gemini-2.0-flash

    The neuron fires on adjectives and adverbs that emphasize or qualify a finding (e.g. “main,” “particular,” “significant,” “possible”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     رفتار
    -0.07
     války
    -0.06
    viewModel
    -0.06
     �
    -0.06
     Bloss
    -0.06
    _provider
    -0.06
     угод
    -0.06
    oltage
    -0.06
    enie
    -0.06
    Interview
    -0.06
    POSITIVE LOGITS
    .annotate
    0.07
    _card
    0.07
    (Constants
    0.07
     #$
    0.07
     pcb
    0.06
     Ae
    0.06
    >↵↵↵
    0.06
     :-↵
    0.06
    pour
    0.06
     ---↵
    0.06
    Act Density 0.042%

    No Known Activations