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

    Neuronpedia

    INDEX
    Explanations

    age

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
     autoFocus
    -0.07
    ینگ
    -0.06
    pegawai
    -0.06
    elho
    -0.06
    оном
    -0.06
     Hopefully
    -0.06
    	Namespace
    -0.06
    ीप
    -0.06
    210
    -0.06
     체
    -0.06
    POSITIVE LOGITS
    개
    0.08
    etleri
    0.07
     etkili
    0.06
     Admiral
    0.06
    灭
    0.06
    _DI
    0.06
     čer
    0.06
    acters
    0.06
    ）↵
    0.06
    京都
    0.06
    Act Density 0.067%

    No Known Activations