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

    Neuronpedia

    INDEX
    Explanations

    closing code blocks and parentheses

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     «
    0.72
    um
    0.71
     Talks
    0.71
     bleiben
    0.70
     Forms
    0.69
    矾
    0.69
     Barber
    0.68
     Portion
    0.68
     reimb
    0.67
     celebrating
    0.67
    POSITIVE LOGITS
     );
    1.27
     )
    1.23
     )$
    1.22
    )$
    1.19
     ).
    1.14
    )$$
    1.12
     )(
    1.11
    );
    1.11
    )"
    1.08
     ){
    1.07
    Act Density 0.199%

    No Known Activations