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

    Neuronpedia

    INDEX
    Explanations

    Common English words

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases used when giving practical advice or instructions (e.g. “offer,” “info,” “call,” “avoid,” “right”).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
     tileSize
    -0.07
    tv
    -0.06
     song
    -0.06
     ville
    -0.06
    urator
    -0.06
     помог
    -0.06
    νοι
    -0.06
    PM
    -0.06
     episodes
    -0.06
    .Static
    -0.06
    POSITIVE LOGITS
     quantify
    0.07
     FAG
    0.06
     Separ
    0.06
     Covered
    0.06
     हट
    0.06
     پرداز
    0.06
     [<
    0.06
    ड़क
    0.06
    Deposit
    0.06
     outputStream
    0.06
    Act Density 0.084%

    No Known Activations