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

    Neuronpedia

    INDEX
    Explanations

    classes

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    leaflet
    -0.07
    ğim
    -0.07
     diluted
    -0.07
    لیل
    -0.07
    (valid
    -0.07
    font
    -0.06
     packs
    -0.06
    ерб
    -0.06
    yw
    -0.06
     gang
    -0.06
    POSITIVE LOGITS
     Milky
    0.07
    ClientRect
    0.06
     ;;
    0.06
    "]."
    0.06
    ической
    0.06
     Penalty
    0.06
    .decorators
    0.06
    ­ing
    0.06
     various
    0.06
    (Language
    0.06
    Act Density 0.099%

    No Known Activations