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

    Neuronpedia

    INDEX
    Explanations

    building addresses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     invalidated
    -0.07
     아래
    -0.07
     believe
    -0.07
    train
    -0.06
    etadata
    -0.06
    ecedor
    -0.06
    .Rotate
    -0.06
    .Debug
    -0.06
    _lazy
    -0.06
     teach
    -0.06
    POSITIVE LOGITS
     Ran
    0.07
     �
    0.07
     jasmine
    0.07
     محصول
    0.06
     colonization
    0.06
     Jasmine
    0.06
                                   ↵
    0.06
    LIGHT
    0.06
    .setBackgroundResource
    0.06
    轮
    0.06
    Act Density 0.025%

    No Known Activations