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

    Neuronpedia

    INDEX
    Explanations

    CEO of Meta?

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Wicked
    0.46
    ስማ
    0.46
    ገኙ
    0.46
     Старки
    0.45
     Герма
    0.44
     Roads
    0.44
    عة
    0.43
     processor
    0.43
     професси
    0.43
     Valuation
    0.43
    POSITIVE LOGITS
    ktron
    0.42
    /
    0.42
     outburst
    0.42
     વિકાસ
    0.42
     दस्तक
    0.42
     estremamente
    0.40
     இறுதியில்
    0.40
    ரே
    0.39
     ke
    0.39
     turist
    0.39
    Act Density 0.003%

    No Known Activations