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

    Neuronpedia

    INDEX
    Explanations

    programming syntax and keywords

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ۳
    0.49
     ૩
    0.46
    ३
    0.42
    <0xBB>
    0.42
    𝟑
    0.39
     treinta
    0.37
    creates
    0.37
    ۳
    0.37
    ૩
    0.37
     পদার্থ
    0.36
    POSITIVE LOGITS
     nové
    0.39
    éfonos
    0.38
    Бы
    0.38
     typer
    0.37
    〆
    0.36
     병
    0.35
     rez
    0.35
     UNC
    0.35
     Unix
    0.34
     Felix
    0.34
    Act Density 0.004%

    No Known Activations