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

    Neuronpedia

    INDEX
    Explanations

    on to

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     على
    0.80
    على
    0.79
     på
    0.73
     pada
    0.69
     روی
    0.68
     trên
    0.67
     ongoing
    0.64
     auf
    0.64
    ongoing
    0.61
     Pada
    0.60
    POSITIVE LOGITS
     behalf
    0.95
     keresztül
    0.64
    estep
    0.63
    coprotein
    0.58
     وعلى
    0.55
    coproteins
    0.54
     steroids
    0.50
    nect
    0.50
    slaught
    0.50
    nections
    0.49
    Act Density 0.015%

    No Known Activations