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

    Neuronpedia

    INDEX
    Explanations

    bill

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     depart
    -0.08
    婆
    -0.06
     Tanzania
    -0.06
     mannen
    -0.06
    朗
    -0.06
     aprend
    -0.06
    طم
    -0.06
    atched
    -0.06
    eros
    -0.06
    Kernel
    -0.06
    POSITIVE LOGITS
     Acid
    0.07
     final
    0.06
    .rate
    0.06
    .Generation
    0.06
     Зап
    0.06
     bilingual
    0.06
     fill
    0.06
    .Book
    0.06
     multit
    0.06
     backpack
    0.06
    Act Density 0.001%

    No Known Activations