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

    Neuronpedia

    INDEX
    Explanations

    execution policy bypass

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     cinq
    0.41
     두
    0.39
    ากร
    0.36
     ২০
    0.36
    siniz
    0.36
     ود
    0.34
    두
    0.34
    ৫০
    0.34
    centerX
    0.34
    deux
    0.34
    POSITIVE LOGITS
    3
    0.53
    ３
    0.46
    ᱓
    0.45
    ૩
    0.42
     ૩
    0.42
     ۳
    0.41
    <0xBB>
    0.40
     ৩
    0.39
    𝟑
    0.39
    ۳
    0.39
    Act Density 0.011%

    No Known Activations