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

    Neuronpedia

    INDEX
    Explanations

    physical objects and materials

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     be
    0.42
     to
    0.36
    .
    0.33
    기술
    0.33
    4
    0.33
    š
    0.33
    공
    0.33
    다고
    0.32
    이었다
    0.32
    {
    0.32
    POSITIVE LOGITS
    il
    0.51
    ik
    0.45
     ንጥረ
    0.45
     නිෂ්
    0.41
    arme
    0.41
    ar
    0.40
    ak
    0.40
    alne
    0.40
    ine
    0.39
     पहने
    0.39
    Act Density 0.667%

    No Known Activations