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

    Neuronpedia

    INDEX
    Explanations

    are

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    σετε
    -0.07
     पश
    -0.06
    +'.
    -0.06
    ser
    -0.06
    75
    -0.06
    .IsNotNull
    -0.06
    tras
    -0.06
     standart
    -0.06
     mercenaries
    -0.06
    /layout
    -0.06
    POSITIVE LOGITS
     Yad
    0.07
     triang
    0.06
    versible
    0.06
     resorts
    0.06
    από
    0.06
     slideshow
    0.06
    Smoke
    0.06
    ené
    0.06
     thaw
    0.06
     rop
    0.06
    Act Density 0.013%

    No Known Activations