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

    Neuronpedia

    INDEX
    Explanations

    complex debated questions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ز
    0.55
    ци
    0.44
    uffling
    0.44
    selling
    0.43
    χω
    0.41
    size
    0.40
    𝘳
    0.40
    purch
    0.39
     खरीदा
    0.39
    緩
    0.39
    POSITIVE LOGITS
    itriangular
    0.45
     ==>
    0.42
    OSO
    0.42
     repositories
    0.42
     Bila
    0.42
     DeSantis
    0.40
     এটিকে
    0.40
     refineries
    0.40
     aman
    0.40
     ซึ่ง
    0.40
    Act Density 0.004%

    No Known Activations