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

    Neuronpedia

    INDEX
    Explanations

    types of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Components
    0.52
     components
    0.51
    components
    0.47
     facets
    0.46
     subcluster
    0.46
    领域
    0.45
     pillars
    0.45
     Themes
    0.44
     पहलुओं
    0.43
     COMPONENTS
    0.43
    POSITIVE LOGITS
     types
    0.64
     commonly
    0.63
    常见的
    0.60
     टाइप्स
    0.54
    タイプの
    0.53
    常見
    0.53
    类型的
    0.52
     бывают
    0.50
     tipos
    0.49
     типов
    0.49
    Act Density 0.026%

    No Known Activations