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

    Neuronpedia

    INDEX
    Explanations

    relationships and dependencies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Untuk
    0.94
    untuk
    0.92
    Untuk
    0.92
     Для
    0.86
    Pentru
    0.85
    Để
    0.85
    StringTo
    0.84
     Để
    0.84
     Чтобы
    0.80
     Pentru
    0.79
    POSITIVE LOGITS
      
    0.76
    <0xC2>
    0.73
    Trusted
    0.60
     ​​
    0.59
     ot
    0.58
     solely
    0.56
    <unused2197>
    0.54
     (
    0.54
     not
    0.54
     fundamentally
    0.52
    Act Density 1.910%

    No Known Activations