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

    Neuronpedia

    INDEX
    Explanations

    survey, tour, audit, retreat

    np_acts-logits-general · gemini-2.5-flash-lite

    educational content and events

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ни
    0.83
    я
    0.76
    ia
    0.71
    ام
    0.71
    t
    0.70
    ai
    0.68
    ด
    0.68
    िक
    0.67
    า
    0.65
    िया
    0.64
    POSITIVE LOGITS
    {
    0.70
    ⁶
    0.65
    ća
    0.62
    ᱘
    0.61
    ၆
    0.60
    YOU
    0.59
    %
    0.59
    />
    0.58
    owaniu
    0.58
    Toxic
    0.58
    Act Density 0.663%

    No Known Activations