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

    Neuronpedia

    INDEX
    Explanations

    ditch the generic

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Likely
    0.39
     ..."
    0.37
     ...,
    0.37
     যেসব
    0.35
     만큼
    0.35
     ву
    0.35
    波动
    0.35
    किंग
    0.34
     любы
    0.34
    醚
    0.34
    POSITIVE LOGITS
     মাদ্র
    0.39
     prodotto
    0.38
    amist
    0.37
     hug
    0.37
     sympt
    0.37
     Per
    0.36
    Produto
    0.36
     Panorama
    0.36
    Fade
    0.36
    lady
    0.36
    Act Density 0.000%

    No Known Activations