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
    Status
    -0.07
     address
    -0.06
     staying
    -0.06
    Iran
    -0.06
     threats
    -0.06
     ó
    -0.06
     strategic
    -0.06
     scholarship
    -0.06
     penalty
    -0.06
    )]↵↵
    -0.06
    POSITIVE LOGITS
    SuccessListener
    0.06
    athroom
    0.06
     článku
    0.06
    ransition
    0.06
     вспом
    0.06
     Frid
    0.06
    _preference
    0.06
     privile
    0.06
    .removeFrom
    0.06
     resized
    0.06
    Act Density 0.013%

    No Known Activations