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

    Neuronpedia

    INDEX
    Explanations

    break down

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     عدم
    0.79
    ۣ
    0.75
    亠
    0.72
    砳
    0.67
    JA
    0.66
    ዲ
    0.66
     иной
    0.64
    是在
    0.64
    EO
    0.62
     együtt
    0.60
    POSITIVE LOGITS
     the
    0.92
     titers
    0.80
    ন
    0.79
    াতিক
    0.78
     their
    0.77
     your
    0.76
     minu
    0.75
    த்தின்
    0.75
     dishes
    0.74
    ه
    0.74
    Act Density 0.149%

    No Known Activations