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

    Neuronpedia

    INDEX
    Explanations

    time runs out, lost bloom, how fast

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     épais
    0.61
     Pä
    0.60
     przede
    0.58
     erinner
    0.57
     produt
    0.56
     cort
    0.55
     održ
    0.55
     Rea
    0.54
     prevenir
    0.54
     ponytail
    0.54
    POSITIVE LOGITS
    0
    0.67
    م
    0.65
    have
    0.59
    วก
    0.59
    ز
    0.55
    relse
    0.53
    ม
    0.51
    im
    0.50
     رخ
    0.50
    هد
    0.49
    Act Density 0.000%

    No Known Activations