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

    Neuronpedia

    INDEX
    Explanations

    rom

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     late
    -0.30
    Side
    -0.30
    late
    -0.30
     paj
    -0.29
    Late
    -0.29
    ForResult
    -0.28
    æݨæµĭ
    -0.27
    次ä¼ļè®®
    -0.26
    çĻ»è®°
    -0.26
     Side
    -0.26
    POSITIVE LOGITS
    hift
    0.27
    åIJ®
    0.27
    etes
    0.26
     Mull
    0.26
    sole
    0.25
     gql
    0.25
    æī¶
    0.24
     gifted
    0.24
    Gre
    0.23
    ãĥĹãĥ¬ãĥ¼
    0.23
    Act Density 0.004%

    No Known Activations