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

    Neuronpedia

    INDEX
    Explanations

    rocket equation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     transcripts
    0.44
    sprecher
    0.38
     Packet
    0.37
    dye
    0.37
     Wm
    0.37
     Transcript
    0.37
     നേതൃ
    0.37
     suitors
    0.35
     Spartan
    0.35
     transplanted
    0.35
    POSITIVE LOGITS
    COVID
    0.46
     приго
    0.40
     ракет
    0.40
    পাল
    0.40
     metaverse
    0.39
     smartwatch
    0.39
    航班
    0.39
    लामा
    0.39
     коронави
    0.39
    UTICAL
    0.39
    Act Density 0.002%

    No Known Activations