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

    Neuronpedia

    INDEX
    Explanations

    and

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     beauty
    -0.08
     wer
    -0.08
     übers
    -0.08
    سی
    -0.07
     உள்ளது
    -0.07
     convenient
    -0.07
     sepanjang
    -0.07
    spring
    -0.07
    πέ
    -0.07
     substitution
    -0.07
    POSITIVE LOGITS
    伙伴
    0.10
     కలిసి
    0.09
     arkadaş
    0.09
    riends
    0.08
    রা
    0.08
    :innen
    0.08
     wife
    0.08
     EVO
    0.08
     representantes
    0.08
     Sofia
    0.08
    Act Density 0.085%

    No Known Activations