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

    Neuronpedia

    INDEX
    Explanations

    code/programming

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     suicides
    -0.08
     astronaut
    -0.07
    -Th
    -0.07
     credits
    -0.06
     tém
    -0.06
     LAN
    -0.06
    ظˆ
    -0.06
     contagious
    -0.06
     Jets
    -0.06
     شناسی
    -0.06
    POSITIVE LOGITS
    .unpack
    0.07
    850
    0.06
    之前
    0.06
    стор
    0.06
    /setup
    0.06
    .setInt
    0.06
     Tail
    0.06
     jeden
    0.06
     principio
    0.06
     DE
    0.06
    Act Density 0.000%

    No Known Activations