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

    Neuronpedia

    INDEX
    Explanations

    Systemic change and solutions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     feast
    -0.07
    린이
    -0.06
    DESCRIPTION
    -0.06
     Ply
    -0.06
     pcs
    -0.06
     priesthood
    -0.06
    -earth
    -0.06
    姓
    -0.06
    輪
    -0.06
     fiberglass
    -0.06
    POSITIVE LOGITS
    ちゃん
    0.06
     teaser
    0.06
     zorunlu
    0.06
    HAL
    0.06
     burge
    0.06
     Aspect
    0.06
    _NOTIFICATION
    0.06
     خانو
    0.06
    .jwt
    0.06
     tentative
    0.06
    Act Density 0.039%

    No Known Activations