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

    Neuronpedia

    INDEX
    Explanations

    programming code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     졸
    -0.07
    737
    -0.07
     relaxing
    -0.06
     Mang
    -0.06
    quit
    -0.06
    吸
    -0.06
     doubted
    -0.06
    (rel
    -0.06
    *(-
    -0.06
    yms
    -0.06
    POSITIVE LOGITS
    스템
    0.06
     Situation
    0.06
    Wonder
    0.06
    а�
    0.06
    ibrator
    0.06
    INESS
    0.06
    बल
    0.06
    Ả
    0.06
    DeviceInfo
    0.06
    Bloc
    0.05
    Act Density 0.330%

    No Known Activations