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

    Neuronpedia

    INDEX
    Explanations

    or

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Leopard
    -0.08
     아이콘
    -0.08
     corrections
    -0.07
    ไร
    -0.07
    рик
    -0.07
    类型
    -0.07
    올
    -0.07
    環
    -0.06
     mejorar
    -0.06
     Speaking
    -0.06
    POSITIVE LOGITS
    lients
    0.06
     anybody
    0.06
     Pablo
    0.06
    YZ
    0.06
    Không
    0.06
     `↵
    0.06
    outdir
    0.06
    mando
    0.06
     shutil
    0.06
    [strlen
    0.06
    Act Density 0.079%

    No Known Activations