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

    Neuronpedia

    INDEX
    Explanations

    first non-space character

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     TG
    0.90
     size
    0.87
     large
    0.85
     GRAD
    0.85
    TG
    0.85
     graded
    0.84
     Grande
    0.82
     age
    0.82
    grad
    0.82
     globalization
    0.82
    POSITIVE LOGITS
     Punj
    0.89
     Wap
    0.87
     invertir
    0.85
     Wab
    0.81
    Aw
    0.81
    Nft
    0.79
     corrid
    0.79
     Wex
    0.78
    Aq
    0.78
    Aub
    0.77
    Act Density 2.666%

    No Known Activations