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

    Neuronpedia

    INDEX
    Explanations

    quantities and levels

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Europe
    0.50
    Europe
    0.49
     anonymous
    0.44
     châu
    0.43
     Office
    0.41
     Anon
    0.41
     Европа
    0.41
     Avrupa
    0.41
    欧洲
    0.41
     Châu
    0.40
    POSITIVE LOGITS
     loudly
    0.38
     unsettling
    0.38
    iscono
    0.38
    量が
    0.37
     &[
    0.36
     causative
    0.36
    ocap
    0.36
    につき
    0.36
     சுற்றி
    0.36
    ❔
    0.36
    Act Density 0.000%

    No Known Activations