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

    Neuronpedia

    INDEX
    Explanations

    string and integer types

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ऑर्गे
    0.39
    妝
    0.38
    shoring
    0.38
    塬
    0.38
     ترب
    0.37
    舔
    0.37
     छत
    0.36
     रिवर्स
    0.36
     संतोष
    0.36
     শরীরে
    0.36
    POSITIVE LOGITS
     string
    1.11
    string
    0.97
     integer
    0.97
     strings
    0.93
    字符串
    0.89
     integers
    0.87
     String
    0.86
    文字列
    0.82
     STRING
    0.80
     scalar
    0.80
    Act Density 0.198%

    No Known Activations