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

    Neuronpedia

    INDEX
    Explanations

    what is an

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.68
     and
    0.63
     Haha
    0.63
     lup
    0.62
     teil
    0.57
    h
    0.57
    '
    0.55
    M
    0.55
     he
    0.54
     computer
    0.54
    POSITIVE LOGITS
    ﹂
    0.83
    ри
    0.68
    ▴
    0.62
    ният
    0.62
    anato
    0.60
    িত্তিক
    0.59
     ноября
    0.57
    ovány
    0.57
    ❂
    0.57
    লীগের
    0.57
    Act Density 0.684%

    No Known Activations