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

    Neuronpedia

    INDEX
    Explanations

    strengthen

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    라도
    -0.06
     thôn
    -0.06
     rogue
    -0.06
     erg
    -0.06
     {-
    -0.06
     dio
    -0.05
    этому
    -0.05
    Channels
    -0.05
     процесса
    -0.05
    ..↵↵
    -0.05
    POSITIVE LOGITS
    Logout
    0.07
    IMPLEMENT
    0.07
    .ylabel
    0.07
    DED
    0.07
     Kullan
    0.07
    ﻟ�
    0.07
     integrated
    0.07
    authorize
    0.07
     forc
    0.07
    _once
    0.07
    Act Density 0.009%

    No Known Activations