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

    Neuronpedia

    INDEX
    Explanations

    completely obliterating

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     yin
    0.42
    訳
    0.42
    ме
    0.41
     sn
    0.39
     ч
    0.38
     recessive
    0.37
     flor
    0.37
    ogical
    0.37
    関連
    0.37
     nt
    0.36
    POSITIVE LOGITS
     devoting
    0.45
    強制
    0.43
    dokka
    0.42
     impide
    0.42
     कस्टम
    0.42
    urón
    0.41
     প্রণাম
    0.41
    ELECTRON
    0.41
     चिकित्स
    0.40
     furlough
    0.40
    Act Density 0.001%

    No Known Activations