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

    Neuronpedia

    INDEX
    Explanations

    numbers

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     tôi
    -0.08
    坐
    -0.06
     Tôi
    -0.06
    tractor
    -0.06
     {}.
    -0.06
    chema
    -0.06
     faithfully
    -0.06
    cznie
    -0.06
     knees
    -0.06
    静
    -0.06
    POSITIVE LOGITS
    ?t
    0.08
     PTSD
    0.07
    CAA
    0.06
    يران
    0.06
     bomber
    0.06
    affe
    0.06
    txn
    0.06
    зано
    0.06
    osyal
    0.06
    .TrimSpace
    0.06
    Act Density 0.117%

    No Known Activations