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

    Neuronpedia

    INDEX
    Explanations

    optimal

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    (Card
    -0.06
    ching
    -0.06
    versations
    -0.06
    ARGE
    -0.06
     interrupt
    -0.06
     entertainment
    -0.06
     SERVICE
    -0.06
     Argentina
    -0.06
    Sets
    -0.06
    (Bundle
    -0.06
    POSITIVE LOGITS
     optimal
    0.10
     WHETHER
    0.08
     Oliver
    0.07
    todos
    0.07
     Tyler
    0.07
     Dense
    0.07
     antlr
    0.07
    .socket
    0.06
    のみ
    0.06
    dü
    0.06
    Act Density 0.008%

    No Known Activations