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

    Neuronpedia

    INDEX
    Explanations

    peaceful repeat vulnerability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    मर्श
    0.39
    煅
    0.37
    jskiej
    0.36
     পরিবর্তে
    0.35
     पॉजिटिव
    0.35
     খাব
    0.35
     کردند
    0.35
     tasmim
    0.35
     کرتا
    0.34
    ProxyAgent
    0.34
    POSITIVE LOGITS
    ஞ்சி
    0.39
    Ar
    0.38
    Fen
    0.37
    adol
    0.37
     Andi
    0.37
     ആശയ
    0.36
     Lois
    0.36
     થો
    0.36
     Av
    0.35
    édi
    0.35
    Act Density 0.004%

    No Known Activations