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

    Neuronpedia

    INDEX
    Explanations

    numbered positions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    াউন্ড
    0.38
     المعروف
    0.38
    odnev
    0.37
     Err
    0.37
    sstream
    0.36
    imentos
    0.35
     cazul
    0.35
    locatorType
    0.35
    DBOutput
    0.35
    farwydd
    0.34
    POSITIVE LOGITS
     position
    1.03
    position
    0.88
     positions
    0.84
     rankings
    0.83
     posição
    0.82
     позиции
    0.81
     posiciones
    0.81
     place
    0.80
    的位置
    0.78
     Position
    0.76
    Act Density 0.009%

    No Known Activations