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

    Neuronpedia

    INDEX
    Explanations

    Code/Math

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ;color
    -0.06
     typeName
    -0.06
     заг
    -0.06
    "display
    -0.06
     vrát
    -0.06
    215
    -0.06
    model
    -0.06
    '<
    -0.06
     совсем
    -0.06
     deser
    -0.05
    POSITIVE LOGITS
     bestellen
    0.08
     Italian
    0.07
     adding
    0.07
    mAh
    0.07
    ob
    0.07
     Lebanese
    0.07
    (by
    0.07
    -init
    0.07
    .Accessible
    0.06
     posicion
    0.06
    Act Density 0.001%

    No Known Activations