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

    Neuronpedia

    INDEX
    Explanations

    )

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    laz
    -0.08
    lots
    -0.06
     bundle
    -0.06
     swath
    -0.06
     شکن
    -0.06
     chat
    -0.06
    eta
    -0.06
    џџџџџџџџ
    -0.06
     fores
    -0.06
     标
    -0.06
    POSITIVE LOGITS
     KUR
    0.07
     violently
    0.07
     charcoal
    0.07
     velk
    0.06
     handgun
    0.06
    DEM
    0.06
    нар
    0.06
     elles
    0.06
     kindly
    0.06
    Impl
    0.06
    Act Density 0.000%

    No Known Activations