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

    Neuronpedia

    INDEX
    Explanations

    Google Search Integration

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    𝗲
    0.99
    𝗶
    0.97
    𝗷
    0.95
    𝗧
    0.93
    সাথে
    0.91
    𝘆
    0.90
     somente
    0.89
    𝗹
    0.89
     Herrera
    0.88
    া
    0.87
    POSITIVE LOGITS
    ineries
    0.91
    n
    0.84
     lecturers
    0.82
     venerable
    0.79
     charming
    0.78
    shaft
    0.77
    ണ്ഡി
    0.77
     Bundan
    0.76
    吃
    0.76
     downright
    0.75
    Act Density 0.000%

    No Known Activations