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
    Density
    -0.07
    usuarios
    -0.06
    Descriptor
    -0.06
     graduate
    -0.06
    _spin
    -0.06
    205
    -0.06
     đông
    -0.06
     September
    -0.06
    \Factory
    -0.06
    Location
    -0.06
    POSITIVE LOGITS
     جن
    0.07
    ONUS
    0.07
    ROAD
    0.07
    UILD
    0.07
    PEAR
    0.06
    vious
    0.06
     Regel
    0.06
    types
    0.06
    brıs
    0.06
     apro
    0.06
    Act Density 0.011%

    No Known Activations