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

    Neuronpedia

    INDEX
    Explanations

    GAN

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Vertex
    -0.07
    Notification
    -0.06
     Feature
    -0.06
    lere
    -0.06
    tim
    -0.06
     Adolescent
    -0.06
     adolescent
    -0.06
     BMC
    -0.06
    broker
    -0.06
     satisfaction
    -0.06
    POSITIVE LOGITS
     göl
    0.07
     marshal
    0.07
     gặp
    0.06
     Giang
    0.06
    ODE
    0.06
    _FAIL
    0.06
     masih
    0.06
     pair
    0.06
     desc
    0.06
    .’
    0.06
    Act Density 0.006%

    No Known Activations