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

    Neuronpedia

    INDEX
    Explanations

    workflow visualization

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ggle
    0.46
    বিষ্য
    0.40
    angani
    0.40
    ))]
    0.38
     phénomènes
    0.37
    千萬
    0.37
     برخی
    0.37
     রাখতে
    0.37
    yphenyl
    0.36
    یسم
    0.35
    POSITIVE LOGITS
     TES
    0.45
     NTR
    0.44
     Oi
    0.41
    𝗧
    0.41
     iam
    0.41
     tém
    0.40
    Allocator
    0.39
     Tema
    0.38
     tes
    0.38
     NT
    0.37
    Act Density 0.000%

    No Known Activations