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

    Neuronpedia

    INDEX
    Explanations

    treatment

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     zelf
    -0.07
     atleast
    -0.06
    aises
    -0.06
    ीएस
    -0.06
    Drawing
    -0.06
    _I
    -0.06
    .Consumer
    -0.06
     Alamofire
    -0.06
     igen
    -0.06
     그는
    -0.06
    POSITIVE LOGITS
     hopeful
    0.08
     사랑
    0.07
     Brittany
    0.07
    醫
    0.07
    勇
    0.07
     Wool
    0.06
     Sydney
    0.06
    death
    0.06
    oy
    0.06
    人の
    0.06
    Act Density 0.001%

    No Known Activations