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

    Neuronpedia

    INDEX
    Explanations

    ret

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     �
    -0.07
    伲
    -0.07
     PHY
    -0.07
     Look
    -0.07
    gether
    -0.07
    擤
    -0.06
    鹃
    -0.06
    克
    -0.06
    ５
    -0.06
    弥漫
    -0.06
    POSITIVE LOGITS
    إجر
    0.07
     Manufacturer
    0.07
    _processing
    0.07
    涉及到
    0.07
     essence
    0.07
     muốn
    0.07
     researched
    0.07
    Queen
    0.07
     Cá
    0.07
    -uri
    0.06
    Act Density 0.001%

    No Known Activations