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

    Neuronpedia

    INDEX
    Explanations

    Police commands

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Seasons
    -0.07
    м
    -0.06
    ableView
    -0.06
    ._↵↵
    -0.06
    UG
    -0.06
     основных
    -0.06
     Years
    -0.06
     noses
    -0.06
    edula
    -0.06
    FPS
    -0.06
    POSITIVE LOGITS
    _readable
    0.07
    іть
    0.06
     Circ
    0.06
     plag
    0.06
    ifest
    0.06
     pollut
    0.06
     DialogInterface
    0.06
    bands
    0.06
     veins
    0.06
    Find
    0.06
    Act Density 0.040%

    No Known Activations