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

    Neuronpedia

    INDEX
    Explanations

    generating code or data

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ——
    0.47
    ——
    0.39
    囤
    0.39
    Veteran
    0.38
    観察
    0.37
     हाम
    0.37
    oporosis
    0.35
    ――
    0.35
     -"
    0.35
     rebate
    0.35
    POSITIVE LOGITS
     requests
    0.50
     Give
    0.46
    请
    0.46
    Please
    0.45
    requests
    0.45
     please
    0.45
     提供
    0.44
     የተለያዩ
    0.44
    提供
    0.43
    please
    0.43
    Act Density 0.023%

    No Known Activations