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

    Neuronpedia

    INDEX
    Explanations

    to maximize or visualize

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    bridge
    0.39
    vedi
    0.38
    battery
    0.38
    ensin
    0.38
    movieId
    0.38
    editing
    0.38
    Delivery
    0.37
    Diesel
    0.37
    cameraId
    0.37
    šnj
    0.37
    POSITIVE LOGITS
     सापेक्ष
    0.41
     alegr
    0.40
     invis
    0.38
     actualizaciones
    0.38
     merges
    0.38
     Assuming
    0.38
     testimonio
    0.37
     محیط
    0.36
     ditampilkan
    0.36
     recuerdos
    0.36
    Act Density 0.000%

    No Known Activations