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

    Neuronpedia

    INDEX
    Explanations

    Addition/repetition

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Navig
    -0.07
    produk
    -0.07
    ivos
    -0.06
     çevre
    -0.06
    ‌شوند
    -0.06
    есь
    -0.06
     pll
    -0.06
    霞
    -0.06
     dd
    -0.06
    ίσω
    -0.06
    POSITIVE LOGITS
    mov
    0.07
     Garlic
    0.07
     falls
    0.07
     wheelchair
    0.06
     후
    0.06
    assessment
    0.06
     involvement
    0.06
     mint
    0.06
    .Dep
    0.06
     garlic
    0.06
    Act Density 0.112%

    No Known Activations