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

    Neuronpedia

    INDEX
    Explanations

    1

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    afety
    -0.08
     Load
    -0.07
    دود
    -0.07
     Abuse
    -0.07
     Respond
    -0.07
    Safety
    -0.07
    送
    -0.06
     cliff
    -0.06
     logger
    -0.06
     cellar
    -0.06
    POSITIVE LOGITS
    _sec
    0.07
    NavigationView
    0.06
    prus
    0.06
     gemeins
    0.06
     ln
    0.06
    nc
    0.06
     ]);↵↵
    0.06
    Tr
    0.06
    -n
    0.06
     periodically
    0.06
    Act Density 0.005%

    No Known Activations