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

    Neuronpedia

    INDEX
    Explanations

    Android API levels

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     bananas
    -0.07
     dinners
    -0.07
    -dropdown
    -0.06
    才
    -0.06
     tob
    -0.06
     lunches
    -0.06
     evangelical
    -0.06
    ively
    -0.06
    atable
    -0.06
    凉
    -0.06
    POSITIVE LOGITS
     تق
    0.06
    _pref
    0.06
    ующий
    0.06
     Produkt
    0.06
    Ø
    0.06
     типу
    0.06
     Contributor
    0.06
     ProductService
    0.06
     얼
    0.06
    _BOUND
    0.06
    Act Density 0.008%

    No Known Activations