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

    Neuronpedia

    INDEX
    Explanations

    use definitions and principles

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    preneurs
    0.45
    bling
    0.36
    ಂಥ
    0.36
    Beauty
    0.35
    äjä
    0.34
    quakes
    0.34
    beauty
    0.33
    ami
    0.33
    proud
    0.33
    consensus
    0.33
    POSITIVE LOGITS
     principles
    0.77
     definitions
    0.66
     conhecimentos
    0.64
     знания
    0.60
     princípios
    0.60
     principes
    0.60
     Principles
    0.58
     properties
    0.58
     knowledge
    0.57
     definition
    0.57
    Act Density 0.027%

    No Known Activations