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

    Neuronpedia

    INDEX
    Explanations

    find

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     adversary
    -0.07
    /Gate
    -0.07
    东西
    -0.07
     poner
    -0.07
    .canvas
    -0.07
     birthdays
    -0.07
    乂
    -0.06
     Ingredients
    -0.06
     neurop
    -0.06
     cloak
    -0.06
    POSITIVE LOGITS
    ообраз
    0.07
    ываем
    0.07
     Timing
    0.06
     inclined
    0.06
     rebuilt
    0.06
    findFirst
    0.06
    訪
    0.06
    "`
    0.06
     offline
    0.06
    ���
    0.06
    Act Density 0.015%

    No Known Activations