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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     Behaviour
    -0.06
    结
    -0.06
    ș
    -0.06
     Economic
    -0.06
    paRepository
    -0.06
     iterator
    -0.06
     spe
    -0.06
     Streaming
    -0.06
     sinister
    -0.06
    菌
    -0.06
    POSITIVE LOGITS
     contestants
    0.07
    .twimg
    0.07
     intoxic
    0.07
    hausen
    0.07
    =date
    0.06
    _unsigned
    0.06
     pleaded
    0.06
    ":"","
    0.06
    .openqa
    0.06
    testdata
    0.06
    Act Density 0.060%

    No Known Activations