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

    Neuronpedia

    INDEX
    Explanations

    one

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    -speaking
    -0.06
    伯
    -0.06
    求
    -0.06
     Everything
    -0.06
    Take
    -0.06
    _nombre
    -0.06
    Author
    -0.06
    製
    -0.06
    По
    -0.06
     Dut
    -0.06
    POSITIVE LOGITS
    _instructions
    0.07
    .Is
    0.07
    irq
    0.07
    (mask
    0.06
    іду
    0.06
    _configs
    0.06
    <byte
    0.06
    ]-$
    0.06
    _Context
    0.06
     arası
    0.06
    Act Density 0.254%

    No Known Activations