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

    Neuronpedia

    INDEX
    Explanations

    node.js require

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    🗸
    0.61
    。\
    0.59
    ⱼ
    0.58
     étro
    0.58
     నియ
    0.57
     AutoML
    0.56
     laboral
    0.55
     jurídica
    0.55
    驀
    0.55
     Áng
    0.55
    POSITIVE LOGITS
    at
    0.67
    ),
    0.63
    tracks
    0.62
    ash
    0.61
    to
    0.60
    डी
    0.59
    ↵
    0.57
    the
    0.57
    table
    0.57
    with
    0.56
    Act Density 0.000%

    No Known Activations