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

    Neuronpedia

    INDEX
    Explanations

    scientific and technical terms

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    दिन
    0.45
    kao
    0.44
    Guitar
    0.43
    Multiple
    0.43
    OSH
    0.42
    kHz
    0.42
    MemberList
    0.42
    Qualification
    0.41
    Telephone
    0.41
    𐰑
    0.41
    POSITIVE LOGITS
    們
    1.25
    们
    1.19
    들을
    1.14
    们的
    1.10
    ‌های
    1.08
    들과
    1.06
    들에
    1.06
     های
    1.04
    들은
    1.03
    들의
    1.03
    Act Density 1.553%

    No Known Activations