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

    Neuronpedia

    INDEX
    Explanations

    Code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    uis
    -0.08
    'ou
    -0.08
    -ee
    -0.08
     राश
    -0.07
     toile
    -0.07
     Narc
    -0.07
     Maxwell
    -0.07
     Yan
    -0.07
     invention
    -0.07
     Riv
    -0.07
    POSITIVE LOGITS
     केर
    0.08
     दौरान
    0.08
     चुन
    0.08
     erstaun
    0.08
     ищ
    0.08
     essentielles
    0.08
     olsem
    0.08
     बीच
    0.08
     namens
    0.07
     необходимые
    0.07
    Act Density 0.050%

    No Known Activations