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

    Neuronpedia

    INDEX
    Explanations

    column names

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     আমির
    0.62
     امر
    0.61
     الح
    0.59
     packages
    0.59
     Packages
    0.58
     Kn
    0.56
     belong
    0.54
     શ્રી
    0.54
     objects
    0.53
    pend
    0.53
    POSITIVE LOGITS
     Cols
    0.88
     colonne
    0.87
     cols
    0.84
     Col
    0.82
     col
    0.82
    col
    0.82
    ocell
    0.77
    Col
    0.77
    Coluna
    0.75
     coluna
    0.75
    Act Density 0.297%

    No Known Activations