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

    Neuronpedia

    INDEX
    Explanations

    biotic, abiotic, fraud, targeting

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    別
    0.43
    AE
    0.42
     DW
    0.38
    chandelier
    0.38
    separate
    0.38
    찍
    0.37
     dwelt
    0.37
    T
    0.37
    ایک
    0.36
    Sonar
    0.36
    POSITIVE LOGITS
     कारक
    0.43
     कारकों
    0.42
     🎉
    0.41
     algum
    0.38
    ப்போ
    0.38
     ?!
    0.38
     கரு
    0.37
    -_-
    0.37
     Kali
    0.37
    🔸
    0.37
    Act Density 0.001%

    No Known Activations