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

    Neuronpedia

    INDEX
    Explanations

    Pro

    np_max-act · gemini-2.0-flash

    The neuron is tuned to spot the “Pro” token in “Pro Se” appellations indicating a self-represented party.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     httpClient
    -0.07
     addictive
    -0.07
    h
    -0.06
    mort
    -0.06
     terk
    -0.06
    .Cancel
    -0.06
    âu
    -0.06
    .........
    -0.06
    icks
    -0.06
     CARD
    -0.06
    POSITIVE LOGITS
    lista
    0.07
     disbelief
    0.06
     plataforma
    0.06
    �
    0.06
    гра
    0.06
     â
    0.06
    Ú
    0.06
    nutí
    0.06
    ırak
    0.06
    NonNull
    0.06
    Act Density 0.000%

    No Known Activations