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

    Neuronpedia

    INDEX
    Explanations

    restrict

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    乌
    -0.08
     attack
    -0.07
    AKE
    -0.07
     дер
    -0.07
    ake
    -0.07
    .ERROR
    -0.06
    osu
    -0.06
     attacks
    -0.06
    bay
    -0.06
    ư�
    -0.06
    POSITIVE LOGITS
     differing
    0.07
     threadIdx
    0.07
     MacDonald
    0.06
     kInstruction
    0.06
     plagiarism
    0.06
    ˆ
    0.06
     veh
    0.06
     عد
    0.06
    sudo
    0.06
     LoggerFactory
    0.06
    Act Density 0.000%

    No Known Activations