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

    Neuronpedia

    INDEX
    Explanations

    given an input string

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ্স
    0.44
     ૩
    0.42
    鏽
    0.42
     メンズ
    0.41
    を守
    0.40
     クリーム
    0.40
    umbia
    0.40
     كور
    0.39
     Ländern
    0.39
     ''),
    0.39
    POSITIVE LOGITS
    Expert
    0.56
    Answer
    0.55
    ANSWER
    0.55
    Solution
    0.54
    Step
    0.53
    Description
    0.53
    उत्तर
    0.52
     Solution
    0.51
    Synopsis
    0.50
     Answer
    0.49
    Act Density 0.000%

    No Known Activations