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

    Neuronpedia

    INDEX
    Explanations

    connect

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    人参
    -0.08
    が多い
    -0.07
    𝐣
    -0.07
    榻
    -0.07
    �
    -0.07
     radios
    -0.07
    ꦥ
    -0.07
    .addItem
    -0.07
    ｼ
    -0.07
    老旧
    -0.07
    POSITIVE LOGITS
    .We
    0.08
     Ab
    0.07
     We
    0.07
     guarantee
    0.07
    導致
    0.07
    邮政
    0.07
    (ticket
    0.07
     OF
    0.06
     For
    0.06
     SQL
    0.06
    Act Density 0.001%

    No Known Activations