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

    Neuronpedia

    INDEX
    Explanations

    qualifications after 'though'

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    （
    0.50
     («
    0.44
    (\
    0.43
     。
    0.42
    (
    0.42
    。「
    0.41
    。
    0.40
     （
    0.39
    0.38
    ̣
    0.38
    POSITIVE LOGITS
    !).
    0.82
    !),
    0.75
    !)
    0.73
    !!)
    0.68
     übrigens
    0.61
     admittedly
    0.60
    ?).
    0.59
    ...).
    0.59
    !);
    0.59
     되겠죠
    0.59
    Act Density 0.140%

    No Known Activations