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

    Neuronpedia

    INDEX
    Explanations

    think step by step

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    RO
    2.14
     avere
    2.05
    ї
    1.90
    ма
    1.83
    can
    1.80
    cu
    1.77
     Є
    1.77
    і
    1.77
    у
    1.65
    мами
    1.64
    POSITIVE LOGITS
    टर
    1.98
    ている
    1.77
    رة
    1.76
    शील
    1.70
     fondly
    1.70
     furrow
    1.69
     aloud
    1.68
    sley
    1.66
    रूप
    1.62
    रण
    1.60
    Act Density 0.313%

    No Known Activations