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

    Neuronpedia

    INDEX
    Explanations

    configuration and options

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Maven
    0.45
     JAR
    0.43
     potion
    0.42
     MEAN
    0.40
    ्रेड
    0.39
     Teh
    0.38
     Vik
    0.38
     Rent
    0.38
     jar
    0.38
     perist
    0.38
    POSITIVE LOGITS
    excludes
    0.49
    getSource
    0.46
    includes
    0.45
     arguments
    0.43
     argumentos
    0.43
    sourceFolder
    0.42
    arguments
    0.40
    configFile
    0.40
    setModel
    0.40
    setGeometry
    0.40
    Act Density 0.001%

    No Known Activations