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

    Neuronpedia

    INDEX
    Explanations

    success

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     olig
    -0.07
    �ng
    -0.07
    भग
    -0.06
     Chatt
    -0.06
    (rect
    -0.06
    Pan
    -0.06
    [N
    -0.06
     ip
    -0.06
     rat
    -0.06
    iliate
    -0.06
    POSITIVE LOGITS
    .Results
    0.07
     Ens
    0.07
    effect
    0.07
     Hercules
    0.07
     hiệu
    0.07
     situaci
    0.07
    ा.
    0.07
    unya
    0.06
     Trouble
    0.06
     lạc
    0.06
    Act Density 0.009%

    No Known Activations