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

    Neuronpedia

    INDEX
    Explanations

    numerical image references

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     hollow
    -0.07
    雷
    -0.07
     المق
    -0.07
     Harr
    -0.07
    .finish
    -0.06
    _traits
    -0.06
     orgy
    -0.06
     Morales
    -0.06
    >R
    -0.06
     orch
    -0.06
    POSITIVE LOGITS
     </
    0.08
    Guest
    0.07
    \xff
    0.07
     UA
    0.06
    reature
    0.06
     Ebay
    0.06
     баг
    0.06
    cheduler
    0.06
    cron
    0.06
     "</
    0.06
    Act Density 0.004%

    No Known Activations