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

    Neuronpedia

    INDEX
    Explanations

    code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     alternate
    -0.07
     BSD
    -0.06
     भग
    -0.06
     bietet
    -0.06
     business
    -0.06
     alcoholic
    -0.06
     Bender
    -0.06
    环
    -0.06
     acceptance
    -0.06
     bundles
    -0.06
    POSITIVE LOGITS
     �
    0.07
     QT
    0.07
    ной
    0.06
    .Question
    0.06
    .gen
    0.06
    .setState
    0.06
     поскольку
    0.06
    serter
    0.06
    "<<
    0.06
    =d
    0.06
    Act Density 0.168%

    No Known Activations