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

    Neuronpedia

    INDEX
    Explanations

    extend and extensions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    chen
    0.49
     seinem
    0.44
    Beau
    0.44
     Beau
    0.42
     aspectos
    0.42
    あたり
    0.41
    澧
    0.41
     prensa
    0.40
    фр
    0.40
    ць
    0.39
    POSITIVE LOGITS
     extens
    0.85
    延伸
    0.83
     extension
    0.80
     extend
    0.77
     EXT
    0.76
     Extension
    0.76
     extending
    0.75
     extender
    0.73
     Ext
    0.73
     Extend
    0.72
    Act Density 0.018%

    No Known Activations