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

    Neuronpedia

    INDEX
    Explanations

    Eddie names and other languages

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    n
    4.36
    te
    3.84
    k
    3.70
    a
    3.58
    ać
    3.49
    nad
    3.39
    nach
    3.09
    nj
    3.01
    ுங்கள்
    2.92
    keb
    2.91
    POSITIVE LOGITS
    একটি
    2.94
    ми
    2.91
     deed
    2.90
    ра
    2.78
    adays
    2.75
    boldsymbol
    2.74
     Бүген
    2.70
     Бүгенге
    2.69
    Ngoài
    2.68
     vutt
    2.68
    Act Density 0.004%

    No Known Activations