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

    Neuronpedia

    INDEX
    Explanations

    Customers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Labor
    -0.07
     Labor
    -0.07
     Jets
    -0.07
    quelle
    -0.07
    뎈
    -0.07
    ינ
    -0.07
    .Offset
    -0.07
     Nationwide
    -0.07
    وي
    -0.07
    连胜
    -0.07
    POSITIVE LOGITS
     gloss
    0.07
    此刻
    0.07
     palette
    0.07
    .userService
    0.06
    博主
    0.06
     amalg
    0.06
    acies
    0.06
     histor
    0.06
     ponieważ
    0.06
    早晨
    0.06
    Act Density 0.178%

    No Known Activations