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

    Neuronpedia

    INDEX
    Explanations

    career

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     karıştır
    -0.07
    .calculate
    -0.07
    /release
    -0.06
    inceton
    -0.06
     Tell
    -0.06
     быть
    -0.06
     kök
    -0.06
     tell
    -0.06
     customs
    -0.06
     rap
    -0.06
    POSITIVE LOGITS
    ）↵
    0.07
    ipped
    0.07
    ……」↵↵
    0.06
    oit
    0.06
    ::$_
    0.06
    �이
    0.06
    /*↵
    0.06
    。」↵↵
    0.06
     CALC
    0.06
     leaderboard
    0.06
    Act Density 0.035%

    No Known Activations