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

    Neuronpedia

    INDEX
    Explanations

    sentiment and appreciation expressions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    :
    0.44
    ,
    0.42
    )
    0.42
    ),
    0.41
    .
    0.38
    ).
    0.36
    }
    0.36
    ;
    0.36
    -
    0.36
     ribbed
    0.32
    POSITIVE LOGITS
     మరింత
    0.52
    ণ্ট
    0.46
    ot
    0.44
    ্জ
    0.44
    ্ঞ
    0.43
    ীষ
    0.43
    ပို
    0.43
    iesz
    0.42
     ವಿಷಯ
    0.42
     видеть
    0.41
    Act Density 0.022%

    No Known Activations