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

    Neuronpedia

    INDEX
    Explanations

    heteroskedasticity

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Adapter
    -0.07
    DRV
    -0.07
     Grad
    -0.06
    =item
    -0.06
    拿来
    -0.06
    ("%
    -0.06
    Ⓞ
    -0.06
    .AddColumn
    -0.06
     projector
    -0.06
    kf
    -0.06
    POSITIVE LOGITS
     brakes
    0.08
    .toggle
    0.08
     בצורה
    0.07
     spills
    0.07
     Delhi
    0.07
     mistake
    0.07
    .delivery
    0.07
     жур
    0.07
     mistakes
    0.07
     Ric
    0.06
    Act Density 0.036%

    No Known Activations