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

    Neuronpedia

    INDEX
    Explanations

    * or 1

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Various
    0.57
     Numerous
    0.54
     Approximately
    0.54
     కూడా
    0.53
    Various
    0.52
     Increasing
    0.52
     زیادی
    0.52
     Probably
    0.50
    Что
    0.50
    Then
    0.50
    POSITIVE LOGITS
    如果
    0.52
     code
    0.46
    建议
    0.45
     powered
    0.44
    如果是
    0.43
     issuing
    0.42
    如果没有
    0.42
     thank
    0.41
    除了
    0.41
     cr
    0.40
    Act Density 0.005%

    No Known Activations