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

    Neuronpedia

    INDEX
    Explanations

    ption

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    folios
    -0.07
     तह
    -0.06
     operation
    -0.06
     drank
    -0.06
    pcf
    -0.06
    -air
    -0.06
    อ
    -0.06
     돈
    -0.06
     lifestyles
    -0.06
    픽
    -0.06
    POSITIVE LOGITS
     السكان
    0.07
    薩
    0.06
    (gray
    0.06
     invoke
    0.06
     직
    0.06
    .clean
    0.06
    _LOGGER
    0.06
    ][:
    0.06
     Chin
    0.06
     हत
    0.06
    Act Density 0.000%

    No Known Activations