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

    Neuronpedia

    INDEX
    Explanations

    run on consumer hardware

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    Supplier
    0.52
    âni
    0.49
    Insurance
    0.49
    நம்
    0.48
    supplier
    0.47
    ани
    0.47
    iciary
    0.46
     খোঁ
    0.46
    न्नी
    0.46
    Chosen
    0.46
    POSITIVE LOGITS
     بدون
    1.03
     without
    1.00
     без
    0.98
     χωρίς
    0.98
     Without
    0.98
     senza
    0.89
     ohne
    0.89
    也能
    0.88
     zonder
    0.88
     WITHOUT
    0.85
    Act Density 0.008%

    No Known Activations