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

    Neuronpedia

    INDEX
    Explanations

    professional followed by role or advice

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ри
    2.14
    ال
    2.14
    ਰ
    2.13
    ر
    1.98
    ن
    1.92
    ري
    1.90
    ∑</
    1.89
    náv
    1.86
    ร์
    1.84
    ها
    1.81
    POSITIVE LOGITS
    cie
    1.67
     ApiException
    1.63
    fico
    1.55
     Fonts
    1.52
    cane
    1.50
    ot
    1.48
    isierung
    1.48
     indignation
    1.47
     faiths
    1.46
     Profesional
    1.46
    Act Density 0.193%

    No Known Activations