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

    Neuronpedia

    INDEX
    Explanations

    names following titles or colons

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
             
    0.36
     Paragraph
    0.32
    <i>
    0.32
            
    0.31
              
    0.31
                         
    0.30
           
    0.30
     ->
    0.30
    WARNING
    0.29
         
    0.29
    POSITIVE LOGITS
     новий
    0.33
     ഹ
    0.33
     優
    0.32
    mila
    0.32
    𒂗
    0.32
    バ
    0.31
     ن
    0.31
    జేపీ
    0.30
     Rizal
    0.30
     בן
    0.30
    Act Density 0.033%

    No Known Activations