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

    Neuronpedia

    INDEX
    Explanations

    number of

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     procé
    0.74
     terá
    0.68
     действу
    0.67
     excite
    0.65
    逘
    0.65
     tradu
    0.64
     corro
    0.64
     trá
    0.64
     tâm
    0.63
     confl
    0.63
    POSITIVE LOGITS
     to
    0.81
    to
    0.72
    ர்
    0.70
    d
    0.70
     Returns
    0.68
     Analytics
    0.66
     प्लेइंग
    0.66
    ě
    0.66
    ų
    0.65
    р
    0.64
    Act Density 0.018%

    No Known Activations