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

    Neuronpedia

    INDEX
    Explanations

    team or researchers at

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    etel
    0.72
    encie
    0.71
     کمر
    0.68
    чень
    0.67
    ottom
    0.65
     حل
    0.65
    льзу
    0.64
    इन
    0.63
    trz
    0.62
    RVCT
    0.62
    POSITIVE LOGITS
     at
    2.66
     tại
    2.29
     atthe
    1.95
     presso
    1.90
     chez
    1.67
     Tại
    1.59
     At
    1.58
    Tại
    1.54
    At
    1.51
     ณ
    1.40
    Act Density 0.193%

    No Known Activations