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

    Neuronpedia

    INDEX
    Explanations

    color shades

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Ram
    0.39
     Ram
    0.38
    illation
    0.38
    sthresh
    0.38
     Kreis
    0.37
    ফা
    0.36
    നെ
    0.36
    OutputStream
    0.36
    赦
    0.36
     Schre
    0.36
    POSITIVE LOGITS
     Hundred
    0.64
     ৪০০
    0.64
     hundred
    0.61
    Hundred
    0.60
     hund
    0.57
     trăm
    0.57
     ৩০০
    0.56
     сот
    0.54
    hundred
    0.52
    三百
    0.52
    Act Density 0.006%

    No Known Activations