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

    Neuronpedia

    INDEX
    Explanations

    multiple languages

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ственное
    -0.09
     rè
    -0.09
    锡
    -0.08
    ственную
    -0.08
    但
    -0.08
     വ്യക്തമാക്കി
    -0.08
    nable
    -0.07
    FFER
    -0.07
     impress
    -0.07
    Nt
    -0.07
    POSITIVE LOGITS
     nor
    0.09
     unbedingt
    0.09
     necessariamente
    0.08
     Nevertheless
    0.07
     lingua
    0.07
    نف
    0.07
     Benefits
    0.07
     weitem
    0.07
     funcionando
    0.07
     necessarily
    0.07
    Act Density 0.123%

    No Known Activations