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

    Neuronpedia

    INDEX
    Explanations

    future events coming

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    a
    0.70
    ه
    0.69
    2
    0.58
    Image
    0.55
    Title
    0.55
    IC
    0.52
    Android
    0.52
    July
    0.52
    Guide
    0.51
    o
    0.51
    POSITIVE LOGITS
     Ủ
    0.59
     professeurs
    0.56
     의료
    0.54
     amélior
    0.54
     sillons
    0.52
     veuillez
    0.52
     pavatt
    0.51
     ateliers
    0.51
     Colle
    0.51
     appren
    0.50
    Act Density 0.000%

    No Known Activations