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

    Neuronpedia

    INDEX
    Explanations

    radio waves and signals

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Update
    0.59
    ↵
    0.56
     prosp
    0.55
    വാദ
    0.54
    1
    0.53
    عار
    0.52
     update
    0.51
     Publishing
    0.50
     महारा
    0.50
    lık
    0.49
    POSITIVE LOGITS
    FileList
    0.56
     συνεχ
    0.54
     мыкты
    0.53
    iobium
    0.52
     हिस्सा
    0.52
    Destination
    0.52
     veniam
    0.51
     வீடு
    0.51
    šť
    0.50
    VENUE
    0.50
    Act Density 0.013%

    No Known Activations