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

    Neuronpedia

    INDEX
    Explanations

    and followed by a surname

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     Drž
    -1.66
    TITUDE
    -1.63
    (),
    -1.62
    -1.62
     etc
    -1.61
    ๗
    -1.61
     برخی
    -1.59
    なども
    -1.57
    などは
    -1.55
    TERY
    -1.54
    POSITIVE LOGITS
      
    1.80
    </i>
    1.79
     dėl
    1.70
    ↵↵
    1.65
    v
    1.59
     Choosing
    1.55
     Practically
    1.54
    ,
    1.54
    それを
    1.52
        
    1.51
    Act Density 0.028%

    No Known Activations