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

    Neuronpedia

    INDEX
    Explanations

    Animal interactions

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     LEGO
    -0.07
     Daughter
    -0.06
     expert
    -0.06
     арми
    -0.06
    _metadata
    -0.06
    |M
    -0.06
     downwards
    -0.06
    adil
    -0.06
    vider
    -0.06
     experience
    -0.06
    POSITIVE LOGITS
     Genel
    0.08
     PGA
    0.07
     explanatory
    0.07
    Neighbors
    0.07
    (ValueError
    0.06
     stata
    0.06
    BarButtonItem
    0.06
     첨부
    0.06
    ners
    0.06
    自動
    0.06
    Act Density 0.043%

    No Known Activations