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

    Neuronpedia

    INDEX
    Explanations

    Programs and optional features

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Namely
    0.50
     Moch
    0.48
     Fir
    0.43
     Siv
    0.42
     SM
    0.42
    ানের
    0.40
     Mans
    0.40
    __))
    0.40
     وه
    0.39
     सिल
    0.39
    POSITIVE LOGITS
     goalie
    0.48
     exorc
    0.43
     дыха
    0.43
    悯
    0.43
     youngsters
    0.43
    保持
    0.42
     испол
    0.42
     राक्ष
    0.42
     музыка
    0.41
     holidays
    0.40
    Act Density 0.000%

    No Known Activations