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

    Neuronpedia

    INDEX
    Explanations

    frequency of knowing/seeing

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     también
    0.32
     также
    0.30
     또한
    0.30
     também
    0.29
     cmap
    0.29
     unable
    0.29
     également
    0.29
     Unable
    0.28
     zarówno
    0.28
     देखील
    0.28
    POSITIVE LOGITS
    睬
    0.38
     guère
    0.32
     overtly
    0.30
     appreciated
    0.30
     appreciate
    0.30
     realise
    0.29
     tepat
    0.29
     know
    0.29
     consciously
    0.29
     apreci
    0.29
    Act Density 0.211%

    No Known Activations