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

    Neuronpedia

    INDEX
    Explanations

    parenthesis

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     UserId
    -0.07
     Maz
    -0.07
     progressives
    -0.07
     outing
    -0.06
     us
    -0.06
     Lodge
    -0.06
     YE
    -0.06
    一個
    -0.06
     Walt
    -0.06
    /id
    -0.06
    POSITIVE LOGITS
     ilaç
    0.07
     forging
    0.07
     参考
    0.06
     rõ
    0.06
    submit
    0.06
     distorted
    0.06
    ुरक
    0.06
    erver
    0.06
     револю
    0.06
    ящих
    0.06
    Act Density 0.005%

    No Known Activations