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

    Neuronpedia

    INDEX
    Explanations

    GPT stands for Generative

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     tslib
    -0.09
     Dodd
    -0.09
     med
    -0.09
     Intr
    -0.09
    gon
    -0.09
     Lump
    -0.08
     RFID
    -0.08
    encias
    -0.08
    Ton
    -0.08
    ÌĨ
    -0.08
    POSITIVE LOGITS
     G
    0.22
     Gener
    0.18
     gener
    0.18
    Gener
    0.17
     stands
    0.15
    ÂłG
    0.14
    stands
    0.13
    G
    0.13
     AI
    0.12
    .G
    0.12
    Act Density 0.074%

    No Known Activations