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

    Neuronpedia

    INDEX
    Explanations

    .dequeueReusableCell

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    权限
    -0.08
    仁
    -0.07
    בד
    -0.07
    ⡱
    -0.07
     Üye
    -0.07
    onio
    -0.06
     "../../../
    -0.06
     tools
    -0.06
     Wildlife
    -0.06
     Emperor
    -0.06
    POSITIVE LOGITS
    -Cola
    0.07
    哩
    0.07
    ัญ
    0.07
    irling
    0.07
    лон
    0.06
    美德
    0.06
    カテゴリ
    0.06
    _symbol
    0.06
    relations
    0.06
    Inter
    0.06
    Act Density 0.001%

    No Known Activations