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

    Neuronpedia

    INDEX
    Explanations

    Sports signings

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    碧
    -0.07
     ):
    -0.07
    짼
    -0.07
    穴
    -0.07
    quisitions
    -0.06
     finely
    -0.06
     rubbing
    -0.06
    "struct
    -0.06
     conc
    -0.06
    箕
    -0.06
    POSITIVE LOGITS
     accepts
    0.08
     Inspired
    0.07
     aconte
    0.07
     Alert
    0.07
    Blob
    0.07
    上が
    0.07
     Failed
    0.07
     unterstüt
    0.07
    Ắ
    0.07
    gpu
    0.07
    Act Density 0.019%

    No Known Activations