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

    Neuronpedia

    INDEX
    Explanations

    mathematical formulas

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    EST
    -0.10
    搞
    -0.09
    COD
    -0.09
     chuyện
    -0.09
    WARE
    -0.08
     ESTE
    -0.08
    Server
    -0.08
    SERVER
    -0.08
    Fight
    -0.08
    _WEB
    -0.08
    POSITIVE LOGITS
     egy
    0.12
     line
    0.11
    line
    0.11
     deriv
    0.10
     differ
    0.10
    .line
    0.10
     hats
    0.10
    -line
    0.10
     komplex
    0.10
     árs
    0.10
    Act Density 0.010%

    No Known Activations