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

    Neuronpedia

    INDEX
    Explanations

    foreign language text snippets

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     wasn
    -0.96
     was
    -0.93
    ższych
    -0.86
     hasn
    -0.82
     чуде
    -0.82
    arpur
    -0.82
     been
    -0.80
     habe
    -0.79
     is
    -0.79
     weren
    -0.78
    POSITIVE LOGITS
     encantó
    0.99
     gustaba
    0.94
     monographs
    0.88
     ecclesias
    0.85
     brun
    0.84
    ྨ
    0.84
     nocturne
    0.83
     Monograph
    0.83
     gustó
    0.82
     fratern
    0.82
    Act Density 0.008%

    No Known Activations