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

    Neuronpedia

    INDEX
    Explanations

    flame

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     chess
    -0.09
     lợi
    -0.08
     processed
    -0.08
    Processed
    -0.07
     retrospective
    -0.07
    _processed
    -0.07
     game
    -0.07
    ोधित
    -0.07
     Fibonacci
    -0.07
     Chess
    -0.07
    POSITIVE LOGITS
     reconhecimento
    0.09
     reconoce
    0.09
     alimentação
    0.09
    idka
    0.09
     안정
    0.08
     fring
    0.08
     nozzle
    0.08
    kräfte
    0.08
     Vape
    0.08
    稳定
    0.08
    Act Density 0.004%

    No Known Activations