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

    Neuronpedia

    INDEX
    Explanations

    by

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Basel
    -0.07
    .Excel
    -0.07
     bại
    -0.06
     boxer
    -0.06
     Angela
    -0.06
     concess
    -0.06
     fw
    -0.06
     Novel
    -0.06
     innings
    -0.06
    (ev
    -0.06
    POSITIVE LOGITS
    ⵔ
    0.08
    StringRef
    0.08
    Петербур
    0.07
    .authenticate
    0.07
    Mountain
    0.07
     largest
    0.07
    Rob
    0.07
    NV
    0.07
    �
    0.07
    Recipient
    0.06
    Act Density 0.002%

    No Known Activations