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

    Neuronpedia

    INDEX
    Explanations

    vehicles and traffic signs

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    /cal
    -0.06
    Rio
    -0.06
     irreversible
    -0.06
     comet
    -0.06
    례
    -0.06
     Ore
    -0.06
     NSIndexPath
    -0.06
     ark
    -0.06
    bubble
    -0.06
     Milton
    -0.06
    POSITIVE LOGITS
     이야
    0.07
    _street
    0.06
    ادة
    0.06
     ам
    0.06
     Ac
    0.06
     FIG
    0.06
     بگیر
    0.06
     значит
    0.06
     CM
    0.06
     db
    0.06
    Act Density 0.038%

    No Known Activations