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

    Neuronpedia

    INDEX
    Explanations

    oil

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    owntown
    -0.07
    包括
    -0.07
     Downtown
    -0.07
     polarization
    -0.06
     downtown
    -0.06
    appers
    -0.06
     forearm
    -0.06
    ewidth
    -0.06
     Packet
    -0.06
     subnet
    -0.06
    POSITIVE LOGITS
     strav
    0.07
     mum
    0.07
    INFRINGEMENT
    0.07
     retir
    0.06
    upported
    0.06
     refin
    0.06
     logger
    0.06
     fır
    0.06
    ≡
    0.06
    inery
    0.06
    Act Density 0.007%

    No Known Activations