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

    Neuronpedia

    INDEX
    Explanations

    used to configure or describe items

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    screenshots
    0.49
     decommission
    0.49
     explosion
    0.45
     outcrop
    0.45
     spille
    0.45
     bookcase
    0.44
    囪
    0.44
     corrugated
    0.44
     whiteboard
    0.44
    myCollision
    0.43
    POSITIVE LOGITS
     ert
    0.46
    蛋白質
    0.45
    ích
    0.44
     保
    0.44
     begeistert
    0.44
    ye
    0.43
     sred
    0.43
    心
    0.43
    jag
    0.43
    ım
    0.42
    Act Density 0.007%

    No Known Activations