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

    Neuronpedia

    INDEX
    Explanations

    commas, parentheses

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    声音
    -0.07
    _sql
    -0.07
     vbox
    -0.06
    .VAL
    -0.06
    صن
    -0.06
    Ін
    -0.06
    計算
    -0.06
    _smart
    -0.06
     Sacred
    -0.06
    .za
    -0.06
    POSITIVE LOGITS
     τό
    0.07
     �
    0.07
     disse
    0.06
     verdiği
    0.06
    一年
    0.06
    _pipeline
    0.06
     reperc
    0.06
     climbed
    0.06
    ��
    0.06
     honey
    0.06
    Act Density 0.011%

    No Known Activations