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

    Neuronpedia

    INDEX
    Explanations

    determiners followed by query words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    box
    0.37
    "
    0.35
     <
    0.34
     "
    0.33
     of
    0.33
     error
    0.32
    filter
    0.32
     to
    0.32
    back
    0.31
    ":
    0.31
    POSITIVE LOGITS
     patitth
    0.33
    akuza
    0.33
    oniazid
    0.32
    ARAJYA
    0.32
    ເຈ
    0.32
    Speaking
    0.31
    ٱ
    0.31
     상당히
    0.31
    を中心
    0.30
    0.30
    Act Density 0.266%

    No Known Activations