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

    Neuronpedia

    INDEX
    Explanations

    feature

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     çerçev
    -0.06
    eckého
    -0.06
    _RST
    -0.06
    uplicates
    -0.06
     dealt
    -0.06
    Ve
    -0.06
     그가
    -0.06
    (tp
    -0.06
     bz
    -0.06
     hiking
    -0.06
    POSITIVE LOGITS
     έχ
    0.06
     Instrument
    0.06
     educate
    0.06
     latency
    0.06
     Electrical
    0.06
    /story
    0.06
     Carry
    0.06
    retry
    0.06
     Mech
    0.06
     ¦
    0.06
    Act Density 0.014%

    No Known Activations