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

    Neuronpedia

    INDEX
    Explanations

    Quotation marks

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    aversal
    -0.06
    یدن
    -0.06
     Bình
    -0.06
    ۱۹۴
    -0.06
    ophile
    -0.06
     ngh
    -0.06
     abandoning
    -0.06
    átel
    -0.06
     절
    -0.05
     begs
    -0.05
    POSITIVE LOGITS
     implications
    0.07
     clearly
    0.07
    vailable
    0.06
    NETWORK
    0.06
     evidently
    0.06
    mq
    0.06
    ا�
    0.06
     счит
    0.06
    ¨ط
    0.06
     LTD
    0.06
    Act Density 0.009%

    No Known Activations