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

    Neuronpedia

    INDEX
    Explanations

    Build-your-own food options

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     arrest
    -0.07
    MD
    -0.07
    ogram
    -0.07
    ioen
    -0.07
     pseudo
    -0.07
    News
    -0.07
    .events
    -0.07
    esia
    -0.07
     condition
    -0.07
     /=
    -0.07
    POSITIVE LOGITS
     toppings
    0.11
     Einrichtungen
    0.09
     السلطة
    0.09
     everyone's
    0.09
     bottled
    0.09
     herkes
    0.09
    Looper
    0.09
     המס
    0.09
     bagi
    0.09
     комплект
    0.08
    Act Density 0.017%

    No Known Activations