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

    Neuronpedia

    INDEX
    Explanations

    discuss

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    Videos
    -0.07
    净
    -0.07
    edException
    -0.07
    Versions
    -0.07
     Allocation
    -0.07
    ATIO
    -0.07
    acos
    -0.07
     Obs
    -0.07
    Med
    -0.07
    无限
    -0.07
    POSITIVE LOGITS
    数学
    0.08
     discussing
    0.07
    &view
    0.07
     wal
    0.07
     discussions
    0.07
     primary
    0.07
    индивидуальн
    0.07
    epend
    0.07
    maint
    0.07
     пло
    0.07
    Act Density 0.042%

    No Known Activations