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

    Neuronpedia

    INDEX
    Explanations

    malicious code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ব্যতীত
    0.48
    vali
    0.45
    necess
    0.44
     крови
    0.44
    টেলে
    0.43
    會在
    0.43
     процентов
    0.43
    orifice
    0.43
     garant
    0.43
    सर्गिक
    0.42
    POSITIVE LOGITS
     Thin
    0.47
     Theory
    0.46
    ೇವೆ
    0.44
     \
    0.43
     Pd
    0.42
     temprano
    0.42
     Semoga
    0.42
    ąd
    0.42
     Yin
    0.42
    idespread
    0.41
    Act Density 0.004%

    No Known Activations