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

    Neuronpedia

    INDEX
    Explanations

    technical reports

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    拼
    -0.07
    吃惊
    -0.07
    eat
    -0.07
    itur
    -0.07
    actus
    -0.07
    皎
    -0.07
    .Scanner
    -0.07
    ⚲
    -0.07
     exit
    -0.07
     nigeria
    -0.07
    POSITIVE LOGITS
     الوز
    0.10
     Governments
    0.07
     administr
    0.07
    abilidade
    0.07
    فق
    0.07
    hosts
    0.07
     Administrative
    0.07
    下面就
    0.07
    Playlist
    0.07
     Champion
    0.07
    Act Density 0.034%

    No Known Activations