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

    Neuronpedia

    INDEX
    Explanations

    print statement or function call

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    س
    0.74
    ubert
    0.73
     Resol
    0.68
     বরং
    0.68
     Jurisdiction
    0.67
    الع
    0.67
     וע
    0.67
    uaje
    0.66
    sman
    0.66
     fern
    0.65
    POSITIVE LOGITS
    [])
    0.80
    ₄
    0.75
    IC
    0.74
     cứ
    0.74
    chis
    0.74
    продук
    0.73
    )’
    0.73
    чительно
    0.73
    ᐟ
    0.73
    テー
    0.72
    Act Density 0.000%

    No Known Activations