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

    Neuronpedia

    INDEX
    Explanations

    date formatting and visual elements

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    グラ
    0.43
    нят
    0.40
    👼
    0.40
     그래
    0.40
     breather
    0.39
     adjective
    0.38
    ହି
    0.37
     merupakan
    0.37
    લી
    0.36
    গ্রহায়ণ
    0.36
    POSITIVE LOGITS
    ia
    0.41
     He
    0.38
    “
    0.38
    mixed
    0.37
     mixed
    0.36
    He
    0.36
    ent
    0.35
    abyrinth
    0.35
    e
    0.35
    st
    0.35
    Act Density 0.003%

    No Known Activations