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

    Neuronpedia

    INDEX
    Explanations

    latest, bleed, curve, True

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     udział
    0.40
     beit
    0.40
    -------------
    0.39
    SCAPE
    0.38
     verdiği
    0.38
     مقاب
    0.38
     участие
    0.37
    fake
    0.36
     fintech
    0.36
    بە
    0.35
    POSITIVE LOGITS
       
    0.58
                       
    0.44
    还是要
    0.42
    Larry
    0.40
     Accessory
    0.39
     Lester
    0.38
    依然
    0.37
    ovies
    0.37
     Bxc
    0.37
     Young
    0.35
    Act Density 0.017%

    No Known Activations