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

    Neuronpedia

    INDEX
    Explanations

    or nor even

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     บาง
    0.43
     неболь
    0.42
    บาง
    0.42
    镛
    0.41
    estrel
    0.40
    itabbo
    0.39
    ･
    0.39
     andRow
    0.38
     ή
    0.37
    በት
    0.37
    POSITIVE LOGITS
     siquiera
    0.94
     any
    0.66
     حتی
    0.66
     nawet
    0.63
     anything
    0.62
     même
    0.62
     qualquer
    0.62
     навіть
    0.62
     even
    0.62
     даже
    0.61
    Act Density 0.109%

    No Known Activations