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

    Neuronpedia

    INDEX
    Explanations

    Scientific research

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ETO
    -0.29
     volumes
    -0.28
    ous
    -0.26
    aman
    -0.26
    анÑĤ
    -0.25
    æŀĹä¸ļ
    -0.25
     lẫn
    -0.25
    -volume
    -0.24
    å½ĴæĿ¥
    -0.24
    aklı
    -0.24
    POSITIVE LOGITS
    ENTS
    0.28
    âľİ
    0.26
    à¸Ńà¸Ńà¸ģ
    0.25
     dictator
    0.25
    Contents
    0.25
    ningen
    0.25
    arters
    0.25
    _der
    0.24
    author
    0.24
    оÑĩно
    0.24
    Act Density 0.941%

    No Known Activations