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

    Neuronpedia

    INDEX
    Explanations

    Hans Zimmer

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    t
    0.84
    ية
    0.81
    ్వ
    0.80
     живо
    0.78
    했다
    0.77
    Mirror
    0.76
    Flutter
    0.75
    സ്
    0.74
     Vân
    0.73
    أة
    0.73
    POSITIVE LOGITS
    ITIES
    0.96
    ﻤ
    0.92
    estones
    0.91
    1
    0.90
    ﮯ
    0.90
    ່ວ
    0.90
     pathTo
    0.90
    2
    0.89
    ﻌ
    0.88
     idempot
    0.88
    Act Density 0.002%

    No Known Activations