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

    Neuronpedia

    INDEX
    Explanations

    921

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    handle
    -0.07
     bulb
    -0.07
     ine
    -0.06
    row
    -0.06
     WF
    -0.06
     translate
    -0.06
     walk
    -0.06
     žádné
    -0.06
     GRAPH
    -0.06
     long
    -0.06
    POSITIVE LOGITS
    .FileName
    0.06
    zn
    0.06
     suspicious
    0.06
    roulette
    0.06
     SDK
    0.06
     XmlNode
    0.06
     contentious
    0.06
    .Cryptography
    0.06
     fixation
    0.06
     قط
    0.06
    Act Density 0.002%

    No Known Activations