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

    Neuronpedia

    INDEX
    Explanations

    describing inclination and manner

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     lepší
    0.23
     einfachen
    0.17
     richtige
    0.17
     richtigen
    0.17
     einfache
    0.17
     continuando
    0.17
     pestaña
    0.17
     gratuite
    0.17
    ريبة
    0.17
     který
    0.17
    POSITIVE LOGITS
     seamlessly
    0.36
     prominently
    0.29
     beautifully
    0.28
     gracefully
    0.28
     intelligently
    0.28
     organically
    0.27
     powerfully
    0.27
     elegantly
    0.27
     smoothly
    0.26
     silently
    0.26
    Act Density 0.711%

    No Known Activations