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

    Neuronpedia

    INDEX
    Explanations

    24/7 availability

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     charities
    0.77
     Charity
    0.70
     or
    0.69
     recientes
    0.68
     violent
    0.67
     donate
    0.67
     punish
    0.67
     oder
    0.65
     violence
    0.65
     respectfully
    0.64
    POSITIVE LOGITS
     nonstop
    1.07
     året
    1.04
    全年
    1.02
     Hours
    1.00
    hours
    0.99
    Hours
    0.99
    Year
    0.99
     hour
    0.98
    ตลอด
    0.95
     suốt
    0.94
    Act Density 0.489%

    No Known Activations