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

    Neuronpedia

    INDEX
    Explanations

    entries following context

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    c
    0.46
    wasm
    0.46
     Houston
    0.45
     nấu
    0.43
     hou
    0.43
    ্লোক
    0.43
    later
    0.42
     开发
    0.42
    ^{*}
    0.40
    those
    0.40
    POSITIVE LOGITS
    ジャ
    0.52
    ంగ్‌
    0.49
    тину
    0.47
    ત
    0.46
    ੰਜਾਬ
    0.46
     signalling
    0.45
     ГӀ
    0.45
    знача
    0.45
    olique
    0.45
     handouts
    0.45
    Act Density 0.001%

    No Known Activations