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

    Neuronpedia

    INDEX
    Explanations

    do, perform

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     значения
    -0.08
    พวก
    -0.06
     μο
    -0.06
    tau
    -0.06
     Bol
    -0.06
    alignment
    -0.06
     vil
    -0.06
    (DEBUG
    -0.06
    "Why
    -0.06
     charms
    -0.06
    POSITIVE LOGITS
    angible
    0.07
    postal
    0.07
     Wikispecies
    0.06
    ApiOperation
    0.06
     deeds
    0.06
    Hashtable
    0.06
    derabad
    0.06
    یه
    0.06
    _latest
    0.06
    _OCCURRED
    0.06
    Act Density 0.071%

    No Known Activations