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

    Neuronpedia

    INDEX
    Explanations

    medical studies

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     brilliance
    -0.07
    õ
    -0.07
    DEVICE
    -0.07
     booking
    -0.06
     carro
    -0.06
     Palestinians
    -0.06
    ालय
    -0.06
     NM
    -0.06
    任务
    -0.06
     luz
    -0.06
    POSITIVE LOGITS
    (identifier
    0.06
     첨부
    0.06
    เสร
    0.06
    -inner
    0.06
     ($_
    0.06
    {},
    0.06
    ğmen
    0.06
    ='".
    0.06
    actable
    0.06
    '^$',
    0.06
    Act Density 0.355%

    No Known Activations