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

    Neuronpedia

    INDEX
    Explanations

    APIs and heterologous expression

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    channel
    -0.66
    Base
    -0.60
     channel
    -0.58
    ed
    -0.54
     grise
    -0.53
    UnusedPrivate
    -0.53
    서는
    -0.52
    y
    -0.52
    way
    -0.50
    api
    -0.49
    POSITIVE LOGITS
     متعلقه
    0.65
    Personensuche
    0.65
    LLocation
    0.65
    Autoritní
    0.64
    tagHelperRunner
    0.64
     OFDb
    0.63
    hoots
    0.63
    ysty
    0.63
    ORAGE
    0.61
    wahati
    0.61
    Act Density 0.123%

    No Known Activations