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

    Neuronpedia

    INDEX
    Explanations

    Begin

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    908
    -0.07
     token
    -0.07
    .Container
    -0.06
    Sale
    -0.06
    퓨
    -0.06
     Sources
    -0.06
    овор
    -0.06
     notifications
    -0.06
    ์ใน
    -0.06
    .Tags
    -0.06
    POSITIVE LOGITS
     incon
    0.07
     Occupy
    0.07
     haf
    0.07
     dishonest
    0.07
     التف
    0.06
    onica
    0.06
    )d
    0.06
    。また
    0.06
    (Il
    0.06
    凡
    0.06
    Act Density 0.001%

    No Known Activations