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

    Neuronpedia

    INDEX
    Explanations

    .org, .png, component

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    DT
    0.80
     marka
    0.78
     Dino
    0.74
     mark
    0.72
    Vin
    0.72
     marca
    0.69
     marques
    0.69
     রেজিম
    0.68
     passenger
    0.68
     bond
    0.68
    POSITIVE LOGITS
    0.54
    وابة
    0.53
     अब्दुल
    0.52
     ABC
    0.50
     আব
    0.50
     Uncertain
    0.49
    sb
    0.49
    icol
    0.48
    ুখ
    0.47
     cí
    0.46
    Act Density 0.240%

    No Known Activations