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

    Neuronpedia

    INDEX
    Explanations

    various contexts

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     குற்றம்
    0.48
     చి
    0.48
     ambao
    0.47
    ekra
    0.46
     मशीन
    0.45
    ᥱ
    0.45
     ដែល
    0.43
     নিয়েছে
    0.43
     violate
    0.42
    ubercul
    0.42
    POSITIVE LOGITS
     Idani
    0.55
    ل
    0.53
    ף
    0.53
    י
    0.52
    用
    0.50
    지
    0.48
    핑
    0.46
    ي
    0.44
    용
    0.44
    <h3>
    0.43
    Act Density 0.001%

    No Known Activations