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

    Neuronpedia

    INDEX
    Explanations

    words starting with Ext

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     जया
    0.89
     unworthy
    0.86
     morphisms
    0.85
     fait
    0.85
     noche
    0.85
     saker
    0.83
     ominous
    0.83
     beyond
    0.82
     eraser
    0.82
     black
    0.82
    POSITIVE LOGITS
    racted
    1.24
    inction
    1.20
    êmement
    1.18
    remely
    1.12
    thiophen
    1.02
    спеди
    0.98
    daction
    0.96
    𝙔
    0.96
    setLocation
    0.96
    rema
    0.96
    Act Density 0.027%

    No Known Activations