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

    Neuronpedia

    INDEX
    Explanations

    code syntax

    np_max-act-logits · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ಡ್
    0.72
    Improvements
    0.69
    .):
    0.68
    ത്തിയത്
    0.67
     हालत
    0.66
    ')}>
    0.65
    }$:
    0.64
     झटका
    0.63
    措施
    0.62
     Improvements
    0.62
    POSITIVE LOGITS
     {}
    1.81
    {}
    1.69
    (){}
    1.44
    ={}
    1.33
    "/>
    1.29
    />
    1.23
     {}\
    1.21
     \\
    1.17
     />
    1.12
    {}\
    1.12
    Act Density 0.268%

    No Known Activations