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

    Neuronpedia

    INDEX
    Explanations

    variable `x` or `X`

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ک
    0.46
    箜
    0.45
     مصنوع
    0.45
     vitth
    0.45
    وران
    0.44
    herme
    0.44
     پلان
    0.43
    0.43
     Hôtel
    0.42
    Asie
    0.42
    POSITIVE LOGITS
     x
    0.94
     X
    0.88
    treme
    0.77
    avier
    0.73
    XXXX
    0.70
    cellent
    0.64
    xxxx
    0.61
    XXXXXXXX
    0.61
    xxx
    0.59
    enia
    0.58
    Act Density 0.060%

    No Known Activations