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

    Neuronpedia

    INDEX
    Explanations

    professional accomplishments

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Wh
    -0.07
    Corners
    -0.07
    -0.07
     अनुस
    -0.07
     ориент
    -0.07
    According
    -0.07
    Bottle
    -0.07
    Foundation
    -0.07
    Paper
    -0.07
    Corner
    -0.06
    POSITIVE LOGITS
     맡
    0.10
     duties
    0.10
    职责
    0.10
     역할
    0.10
     responsibilities
    0.10
     übernommen
    0.09
     هست
    0.09
     presso
    0.09
     emer
    0.09
    esseur
    0.09
    Act Density 0.133%
    No Known Activations