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

    Neuronpedia

    INDEX
    Explanations

    say Dec

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Bluff
    -0.08
    .elasticsearch
    -0.08
    zbollah
    -0.08
     QByte
    -0.08
     नभ
    -0.08
     obscene
    -0.08
    通販
    -0.08
    ầng
    -0.08
    uzzo
    -0.08
     searching
    -0.08
    POSITIVE LOGITS
     autonomy
    0.17
     autonomía
    0.16
     Dec
    0.15
     intrinsic
    0.15
    Intrinsic
    0.14
    Ryan
    0.14
    Dec
    0.14
     autonomia
    0.13
    intr
    0.13
     Intr
    0.13
    Act Density 0.003%

    No Known Activations