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

    Neuronpedia

    INDEX
    Explanations

    including X

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ﻟ
    1.24
     nourished
    1.18
    ని
    1.16
    אי
    1.15
     accentuated
    1.05
    ੀ
    1.05
    ﺪ
    1.04
    <0x92>
    1.02
     ਤੋਂ
    1.02
    ﻪ
    1.00
    POSITIVE LOGITS
    ah
    1.52
    é
    1.49
    ot
    1.48
     également
    1.42
    IN
    1.34
    ens
    1.33
    it
    1.30
     solcher
    1.30
    ut
    1.29
     pleinement
    1.29
    Act Density 0.210%

    No Known Activations