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

    Neuronpedia

    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ▼
    -0.08
    (match
    -0.07
    時期
    -0.07
    前一天
    -0.07
    信箱
    -0.07
     unanimously
    -0.07
     ci
    -0.07
     revelation
    -0.07
     Julien
    -0.07
     nur
    -0.06
    POSITIVE LOGITS
     ổn
    0.08
    capitalize
    0.07
    ↸
    0.07
     Л
    0.07
    羼
    0.07
    GetX
    0.07
    氆
    0.07
    萜
    0.07
    篯
    0.07
    cq
    0.07
    Act Density 0.024%

    No Known Activations