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

    Neuronpedia

    INDEX
    Explanations

    array indexing/mathematical notation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     governments
    -0.09
     América
    -0.07
     anteced
    -0.07
     vanuit
    -0.07
     Senhor
    -0.07
    선
    -0.07
    berto
    -0.07
    .Inventory
    -0.06
     yak
    -0.06
    FIFO
    -0.06
    POSITIVE LOGITS
     শেষে
    0.11
     చివ
    0.08
     конце
    0.08
     শেষ
    0.08
     Plateau
    0.08
     સુધી
    0.07
     পর্যন্ত
    0.07
     پایان
    0.07
    所有
    0.07
     finale
    0.07
    Act Density 0.035%

    No Known Activations