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

    Neuronpedia

    INDEX
    Explanations

    than

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    降
    -0.07
     pollen
    -0.06
     "../
    -0.06
    individual
    -0.06
     đường
    -0.06
     drops
    -0.06
     trial
    -0.06
     玩家
    -0.06
    olicies
    -0.06
    (withIdentifier
    -0.06
    POSITIVE LOGITS
    入れ
    0.07
     Zá
    0.06
    classes
    0.06
    .execution
    0.06
     亚
    0.06
    .assertFalse
    0.06
     Since
    0.06
     Specifically
    0.06
     SECRET
    0.06
     strawberry
    0.06
    Act Density 0.012%

    No Known Activations