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

    Neuronpedia

    INDEX
    Explanations

    material and color specifications

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     %>'
    0.44
    锆
    0.43
    笕
    0.41
    กร
    0.40
    طانیہ
    0.40
    আপনি
    0.39
    まだまだ
    0.38
    疥
    0.38
     पॉइंट
    0.38
     ))->
    0.37
    POSITIVE LOGITS
     G
    0.48
     N
    0.48
     Q
    0.45
     affiliated
    0.43
     E
    0.42
     W
    0.41
     Parr
    0.41
    ner
    0.40
     V
    0.40
     an
    0.40
    Act Density 0.000%

    No Known Activations