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

    Neuronpedia

    INDEX
    Explanations

    a

    np_max-act · gemini-2.0-flash

    The neuron fires on the stock explanatory language used to introduce or describe name suggestions—phrases like “This name…,” “suggests,” “implies,” or “plays on.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Negative Logits
    =password
    -0.07
    Extras
    -0.07
     slander
    -0.07
    สำเร
    -0.06
     dospěl
    -0.06
     مقایسه
    -0.06
    wnd
    -0.06
    .strings
    -0.06
    kám
    -0.06
    できない
    -0.06
    POSITIVE LOGITS
     sólo
    0.06
     Lad
    0.06
     These
    0.06
     Sau
    0.06
    ahy
    0.06
    rompt
    0.06
    RW
    0.06
     Frauen
    0.06
     Mic
    0.06
     BR
    0.06
    Act Density 0.024%

    No Known Activations