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

    Neuronpedia

    INDEX
    Explanations

    mental health resources

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     ವ್ಯಾ
    0.70
    دخل
    0.64
     V
    0.64
    threading
    0.62
    agawa
    0.62
    ölt
    0.60
     blí
    0.60
     Cull
    0.60
     C
    0.59
    </body>
    0.59
    POSITIVE LOGITS
    গাঁ
    0.82
     Banquet
    0.79
     assimilated
    0.76
     beban
    0.75
     confer
    0.72
    睉
    0.72
     trò
    0.70
    UseDebug
    0.69
    পত
    0.68
     расте
    0.67
    Act Density 0.061%

    No Known Activations