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

    Neuronpedia

    INDEX
    Explanations

    interest rate formulas

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    can
    0.43
    क्षित
    0.43
    ల
    0.42
    ю
    0.40
    яв
    0.39
    yc
    0.39
    czas
    0.39
    gara
    0.39
    లు
    0.39
    ხვ
    0.38
    POSITIVE LOGITS
     a
    0.43
     的
    0.41
    迷你
    0.40
     accepting
    0.40
     P
    0.39
     skirm
    0.39
     \{
    0.39
     rotary
    0.39
     ^{
    0.39
    ဖြစ်သည်။
    0.39
    Act Density 0.000%

    No Known Activations