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

    Neuronpedia

    INDEX
    Explanations

    Porter's Five Forces

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     обеща
    0.45
    वरों
    0.39
     deepened
    0.38
    बद्दल
    0.38
     দিতে
    0.37
     הז
    0.37
    ⵜ
    0.37
     இருக்கும்
    0.37
     Hush
    0.36
    忿
    0.36
    POSITIVE LOGITS
    Como
    0.38
    colours
    0.37
    Traditional
    0.37
     Как
    0.37
    仯
    0.36
    poser
    0.36
    Як
    0.35
    ubu
    0.35
    CIR
    0.35
     horizon
    0.34
    Act Density 0.001%

    No Known Activations