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

    Neuronpedia

    INDEX
    Explanations

    responds in English

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     contabil
    0.41
     письмо
    0.39
    шчы
    0.38
     rédaction
    0.38
     չ
    0.37
     Василь
    0.37
     gái
    0.37
    되지
    0.37
     choć
    0.37
     אך
    0.37
    POSITIVE LOGITS
     சிவன்
    0.38
    -\\
    0.38
    abelian
    0.38
    νας
    0.37
    out
    0.36
     because
    0.35
    hedron
    0.35
    return
    0.35
    因為
    0.35
    porque
    0.35
    Act Density 0.008%

    No Known Activations