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

    Neuronpedia

    INDEX
    Explanations

    impersonation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    229
    -0.06
     Jones
    -0.06
    ники
    -0.06
    ippet
    -0.06
    Jones
    -0.06
     сест
    -0.06
     kombin
    -0.06
    =os
    -0.06
     def
    -0.06
    _RX
    -0.06
    POSITIVE LOGITS
    рь
    0.07
     всё
    0.07
     Rebellion
    0.06
    /Foundation
    0.06
    !!!↵↵
    0.06
    길
    0.06
    Qué
    0.06
    aspers
    0.06
     unwanted
    0.06
    $options
    0.06
    Act Density 0.029%

    No Known Activations