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

    Neuronpedia

    INDEX
    Explanations

    large file command

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    aughey
    0.42
     Episodes
    0.39
     तुल
    0.38
     encapsulates
    0.38
     Mormon
    0.37
    बीएस
    0.37
    াইড
    0.37
     calcS
    0.36
    ையா
    0.36
     Migration
    0.36
    POSITIVE LOGITS
     PI
    0.41
     ordine
    0.37
    椥
    0.37
     ago
    0.37
     Ago
    0.37
    टना
    0.37
    熙
    0.37
     heli
    0.36
     Пе
    0.36
     position
    0.35
    Act Density 0.004%

    No Known Activations