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

    Neuronpedia

    INDEX
    Explanations

    access fully

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     nějak
    0.85
     некоторых
    0.80
     někter
    0.78
     somewhat
    0.78
     goodwill
    0.75
     acho
    0.72
     niektórych
    0.71
     சிறிது
    0.70
     sebagainya
    0.70
     alguns
    0.70
    POSITIVE LOGITS
     абсолютно
    1.00
     exquisitely
    0.95
     véritable
    0.91
     FULL
    0.88
     potpuno
    0.86
     огром
    0.86
     unrivalled
    0.86
     повністю
    0.86
     fully
    0.85
     völlig
    0.85
    Act Density 1.090%

    No Known Activations