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

    Neuronpedia

    INDEX
    Explanations

    ICU

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    乡村
    -0.07
     proposes
    -0.07
     shake
    -0.07
    anz
    -0.07
    ел
    -0.07
    年开始
    -0.07
    Scalars
    -0.07
    avigator
    -0.07
    _KIND
    -0.07
    🐑
    -0.07
    POSITIVE LOGITS
     Stuttgart
    0.08
    您
    0.07
    itchen
    0.07
    ปลอด
    0.07
    ||↵
    0.07
     execut
    0.07
    Market
    0.07
     seçim
    0.07
     dati
    0.07
    ffective
    0.07
    Act Density 0.004%

    No Known Activations