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
     ItemType
    -0.08
     iht
    -0.08
    ็นท
    -0.07
    лючается
    -0.07
    .website
    -0.07
     Houston
    -0.07
    Johnson
    -0.06
     horses
    -0.06
     errno
    -0.06
     tzv
    -0.06
    POSITIVE LOGITS
    Ak
    0.08
    bas
    0.07
    ak
    0.07
    kar
    0.07
     alphabet
    0.07
    ruk
    0.07
    ард
    0.07
    روف
    0.07
    κά
    0.07
    ?]
    0.07
    Act Density 0.018%

    No Known Activations