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

    Neuronpedia

    INDEX
    Explanations

    LaTeX figure components

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    л
    0.77
    м
    0.75
    ни
    0.65
    чане
    0.64
    лдуу
    0.59
    servers
    0.57
    اتها
    0.57
    чва
    0.57
    ONTO
    0.57
    น์โหลด
    0.57
    POSITIVE LOGITS
    ).
    0.66
     an
    0.59
     meditative
    0.59
        
    0.58
     as
    0.58
     is
    0.57
     ascertain
    0.56
    pathetic
    0.55
     by
    0.54
    rit
    0.54
    Act Density 0.001%

    No Known Activations