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

    Neuronpedia

    INDEX
    Explanations

    Locations

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     jump
    -0.07
    �부
    -0.07
     bew
    -0.07
    럭
    -0.06
     everything
    -0.06
     Waves
    -0.06
    DS
    -0.06
     reboot
    -0.06
     EventType
    -0.06
     sik
    -0.06
    POSITIVE LOGITS
    ･･
    0.07
     tim
    0.07
     \
    0.07
     appet
    0.07
    Facade
    0.06
    ailure
    0.06
    عف
    0.06
    drug
    0.06
    0.06
     iCloud
    0.06
    Act Density 0.040%

    No Known Activations