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

    Neuronpedia

    INDEX
    Explanations

    negation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .Dispatcher
    -0.07
     όπου
    -0.07
    Clip
    -0.07
    /Framework
    -0.07
     Sap
    -0.07
     ],↵↵
    -0.06
    _MA
    -0.06
    (training
    -0.06
     підвищ
    -0.06
    糖
    -0.06
    POSITIVE LOGITS
    xxx
    0.06
     every
    0.06
     Highest
    0.06
     iff
    0.06
    .isSuccess
    0.06
    597
    0.06
     persuade
    0.06
    isser
    0.06
    Steel
    0.06
    <=(
    0.06
    Act Density 0.006%

    No Known Activations