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

    Neuronpedia

    INDEX
    Explanations

    nonlinear autoregressive network

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    듄
    0.39
     साझेदारी
    0.38
    oids
    0.38
    阝
    0.38
    亩
    0.38
    飞行
    0.37
    धारक
    0.36
    siblings
    0.36
    ၈
    0.36
    최
    0.35
    POSITIVE LOGITS
     univers
    0.41
    jede
    0.39
     choral
    0.39
     beragam
    0.39
     varias
    0.39
    Callbacks
    0.39
     task
    0.38
     klass
    0.38
    OutputType
    0.38
     unity
    0.38
    Act Density 0.002%

    No Known Activations