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

    Neuronpedia

    INDEX
    Explanations

    the start of a sentence

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    _
    0.32
    and
    0.32
    un
    0.31
    ob
    0.30
    ar
    0.30
    ang
    0.30
    al
    0.29
    it
    0.29
    rän
    0.29
    ab
    0.28
    POSITIVE LOGITS
    .
    0.30
    ®.
    0.28
     unsuccessfully
    0.28
    ﻚ
    0.28
     моём
    0.25
    ۔
    0.25
     ผม
    0.25
     abruptly
    0.25
    मैंने
    0.25
    ཨ
    0.24
    Act Density 0.000%

    No Known Activations