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

    Neuronpedia

    INDEX
    Explanations

    undefined mathematical operations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     꾸
    -0.09
    setq
    -0.07
    dr
    -0.07
    thu
    -0.07
     adv
    -0.07
     YYYY
    -0.07
     मद
    -0.07
     commits
    -0.07
     abundant
    -0.07
     reproduction
    -0.07
    POSITIVE LOGITS
    无法
    0.11
     Undefined
    0.11
    Undefined
    0.11
     невозмож
    0.10
     невозможно
    0.10
     ambiguous
    0.10
    Cannot
    0.09
    undefined
    0.09
     avoided
    0.09
    যোগ্য
    0.09
    Act Density 0.035%

    No Known Activations