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

    Neuronpedia

    INDEX
    Explanations

    code delimiters

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    _SYSTEM
    -0.07
     с
    -0.07
    ，都
    -0.06
     نس
    -0.06
     exploited
    -0.06
     chores
    -0.06
     avoid
    -0.06
     раск
    -0.06
    ियत
    -0.06
     telling
    -0.06
    POSITIVE LOGITS
     söylem
    0.07
    FI
    0.06
     '':↵
    0.06
    انون
    0.06
     '''↵↵
    0.06
     počtu
    0.06
     Messaging
    0.06
     Administrative
    0.06
    Rew
    0.06
     sigh
    0.06
    Act Density 0.009%

    No Known Activations