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

    Neuronpedia

    INDEX
    Explanations

    how to instructions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    א
    0.47
    ром
    0.43
     ราช
    0.40
    LuaPush
    0.40
    RawO
    0.40
    า
    0.40
    elow
    0.39
    电流
    0.39
     الرخصة
    0.39
    ەیە
    0.39
    POSITIVE LOGITS
     develop
    0.56
     participate
    0.51
     tinkering
    0.50
     carve
    0.49
    )
    0.49
     geek
    0.48
     video
    0.48
     lap
    0.47
     desarroll
    0.47
     formulate
    0.47
    Act Density 0.002%

    No Known Activations