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

    Neuronpedia

    INDEX
    Explanations

    in

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    帝
    -0.08
    全资子
    -0.07
    垕
    -0.07
     Allen
    -0.07
     sensational
    -0.07
     iterate
    -0.07
     Cone
    -0.07
    _control
    -0.07
    钠
    -0.07
    Cumh
    -0.07
    POSITIVE LOGITS
    _possible
    0.07
    降到
    0.07
    也将
    0.07
     XP
    0.07
    Scripts
    0.07
    ,and
    0.06
    _topic
    0.06
     更新
    0.06
     individ
    0.06
    subtract
    0.06
    Act Density 0.030%

    No Known Activations