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

    Neuronpedia

    INDEX
    Explanations

    engine, force, tool, machine

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    to
    0.72
    as
    0.70
    is
    0.68
    ul
    0.66
    m
    0.61
    of
    0.59
    ad
    0.59
     be
    0.58
    on
    0.53
    де
    0.53
    POSITIVE LOGITS
     opcode
    0.48
    :
    0.42
     responde
    0.41
     mainframe
    0.41
     dynamism
    0.41
     jaoks
    0.40
     जिन्होंने
    0.40
    I
    0.39
     that
    0.39
    สำหรับ
    0.38
    Act Density 0.198%

    No Known Activations