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

    Neuronpedia

    INDEX
    Explanations

    news

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .sup
    -0.07
     ши
    -0.07
     Canc
    -0.07
     обо
    -0.07
     плит
    -0.06
     apprent
    -0.06
    921
    -0.06
    >xpath
    -0.06
     спож
    -0.06
    rail
    -0.06
    POSITIVE LOGITS
    นต
    0.07
    contents
    0.07
     Twins
    0.06
     nên
    0.06
    Instagram
    0.06
     Erica
    0.06
    خص
    0.06
    -rad
    0.06
    grounds
    0.06
     maxSize
    0.06
    Act Density 0.000%

    No Known Activations