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

    Neuronpedia

    INDEX
    Explanations

    ve

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hare
    -0.06
    luet
    -0.06
    $client
    -0.06
    该
    -0.06
     ATA
    -0.06
    áze
    -0.06
     daha
    -0.06
    entication
    -0.06
    oran
    -0.06
     SCAN
    -0.06
    POSITIVE LOGITS
     rotations
    0.07
    actable
    0.06
    ;");↵
    0.06
     citiz
    0.06
    Bloc
    0.06
     four
    0.06
     peasants
    0.06
     ounces
    0.06
    ким
    0.06
     Protected
    0.06
    Act Density 0.106%

    No Known Activations