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

    Neuronpedia

    INDEX
    Explanations

    course descriptions and code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Wiktionnaire
    -0.63
    hoeddwyd
    -0.55
    inkt
    -0.47
     religieux
    -0.46
    ineno
    -0.46
     Posted
    -0.45
    ğından
    -0.44
     député
    -0.44
    thèse
    -0.43
     retrou
    -0.42
    POSITIVE LOGITS
    complexContent
    0.81
     ModelExpression
    0.69
     Vikipedi
    0.67
    IBOutlet
    0.65
     help
    0.65
    nologies
    0.60
    MLLoader
    0.59
    ImageContext
    0.59
     enable
    0.57
    wijl
    0.57
    Act Density 0.005%

    No Known Activations