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

    Neuronpedia

    INDEX
    Explanations

    Punctuation and "and"

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    عادة
    -0.07
    hot
    -0.06
    ENCHMARK
    -0.06
    Boot
    -0.06
    optional
    -0.06
     같
    -0.06
    思
    -0.05
    银行
    -0.05
     deltas
    -0.05
     서비스
    -0.05
    POSITIVE LOGITS
    ADM
    0.07
    _component
    0.07
    ?><
    0.07
    .webdriver
    0.06
     puan
    0.06
    섭
    0.06
     musel
    0.06
     undue
    0.06
     ner
    0.06
     rospy
    0.06
    Act Density 0.126%

    No Known Activations