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

    Neuronpedia

    INDEX
    Explanations

    internet drama, quirks, and media

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ार्टम
    0.46
    ---------*/
    0.44
    忧
    0.43
     उन्‍हें
    0.42
    றிவு
    0.42
    惀
    0.42
    recon
    0.41
    anız
    0.41
    +}$
    0.41
    vii
    0.41
    POSITIVE LOGITS
     to
    0.56
     by
    0.52
    NO
    0.51
     oleh
    0.50
    ة
    0.46
    ObjectClass
    0.45
     rosem
    0.44
    OT
    0.43
    я
    0.42
     بواسطة
    0.42
    Act Density 0.001%

    No Known Activations