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

    Neuronpedia

    INDEX
    Explanations

    {{

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Eb
    -0.07
     tbl
    -0.06
     与
    -0.06
    abe
    -0.06
     tp
    -0.06
     Enough
    -0.06
    樹
    -0.06
     pas
    -0.06
     hồng
    -0.06
     Pol
    -0.06
    POSITIVE LOGITS
     addons
    0.07
    fant
    0.07
     Northwest
    0.06
     purchasing
    0.06
     Kashmir
    0.06
     UFC
    0.06
     Май
    0.06
     Sierra
    0.06
    なん
    0.06
     accomplished
    0.06
    Act Density 0.001%

    No Known Activations