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
    lection
    -0.07
     orden
    -0.07
     reply
    -0.06
    (obs
    -0.06
    通信
    -0.06
     Jail
    -0.06
     bids
    -0.06
    _sleep
    -0.06
     chịu
    -0.06
    	ss
    -0.06
    POSITIVE LOGITS
    )index
    0.07
     karar
    0.06
    "]=$
    0.06
    ebilir
    0.06
    }*
    0.06
    ��
    0.06
    ♪↵↵
    0.06
     onChangeText
    0.06
    ゴリ
    0.06
    ！↵
    0.06
    Act Density 0.054%

    No Known Activations