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

    Neuronpedia

    INDEX
    Explanations

    package

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Help
    -0.07
     obten
    -0.07
     robes
    -0.06
     dissip
    -0.06
     Seats
    -0.06
    plash
    -0.06
     Clown
    -0.06
     leveraging
    -0.06
    share
    -0.06
    -size
    -0.06
    POSITIVE LOGITS
    (rd
    0.07
     aliqua
    0.07
    _ray
    0.07
    kommen
    0.06
     špat
    0.06
    ål
    0.06
     unr
    0.06
    -UA
    0.06
    _hom
    0.06
    (frame
    0.06
    Act Density 0.001%

    No Known Activations