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

    Neuronpedia

    INDEX
    Explanations

    node attributes and settings

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     factor
    0.97
    feature
    0.89
    factor
    0.87
    requirement
    0.86
     feature
    0.84
     fator
    0.83
    option
    0.80
     option
    0.80
    ையாள
    0.78
    resource
    0.78
    POSITIVE LOGITS
     virtues
    1.88
     attributes
    1.78
     qualities
    1.75
     traits
    1.73
     abilities
    1.72
     variables
    1.71
    attributes
    1.68
     goodies
    1.68
     amenities
    1.67
     constants
    1.66
    Act Density 3.302%

    No Known Activations