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

    Neuronpedia

    INDEX
    Explanations

    AP IaC internet insurance

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Phe
    0.65
     Fuller
    0.64
    覇
    0.64
     वरुण
    0.63
     Beau
    0.60
    चुरी
    0.59
    菩
    0.59
     Phu
    0.58
     वसु
    0.58
    ழ்
    0.57
    POSITIVE LOGITS
     Ин
    1.89
     イン
    1.82
    Ин
    1.75
    イン
    1.74
     IM
    1.67
     IR
    1.66
    อิน
    1.66
     ин
    1.66
     İ
    1.62
    Int
    1.60
    Act Density 5.443%

    No Known Activations