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

    Neuronpedia

    INDEX
    Explanations

    lethal/dangerous

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    .tools
    -0.07
    templates
    -0.07
    LINK
    -0.07
     Pak
    -0.06
     Terrorism
    -0.06
    .Utilities
    -0.06
     QVBoxLayout
    -0.06
    jev
    -0.06
    웨
    -0.06
    έντ
    -0.06
    POSITIVE LOGITS
    FS
    0.06
    #####
    0.06
    ).↵↵↵↵
    0.06
     soph
    0.06
     \↵↵
    0.06
     reinc
    0.06
     ROS
    0.06
     SAN
    0.06
    #
    0.06
     sea
    0.06
    Act Density 0.085%

    No Known Activations