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

    Neuronpedia

    INDEX
    Explanations

    conditional statement, sentiment analysis, origin details

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     booths
    0.42
     wand
    0.39
     portray
    0.38
     centered
    0.38
     infused
    0.38
     traditions
    0.37
     caracter
    0.37
     cube
    0.37
     interact
    0.37
     traditional
    0.36
    POSITIVE LOGITS
     satisfactorily
    0.47
    inskii
    0.46
     удовле
    0.46
     беше
    0.42
     компен
    0.42
     Significantly
    0.41
     освобо
    0.41
     выпла
    0.41
    oggio
    0.41
     Publishers
    0.39
    Act Density 0.001%

    No Known Activations