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

    Neuronpedia

    INDEX
    Explanations

    customer or client

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ?
    0.47
    ۔
    0.44
    は
    0.37
    נים
    0.36
     désormais
    0.35
    נ
    0.35
     کې
    0.34
    !
    0.34
    วิธี
    0.33
    人は
    0.33
    POSITIVE LOGITS
    ad
    0.51
    ang
    0.44
    im
    0.44
    ik
    0.43
    ap
    0.43
     customers
    0.42
    ir
    0.41
    0
    0.40
    il
    0.40
    em
    0.40
    Act Density 0.302%

    No Known Activations