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

    Neuronpedia

    INDEX
    Explanations

    Unraid, Social Determinants, Daniel

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ")}}
    0.46
    )}}
    0.41
    0.41
     (`
    0.39
    ffi
    0.38
    getResponse
    0.37
    )}},
    0.37
    例文帳に追加
    0.37
    ϖ
    0.37
    })}\
    0.36
    POSITIVE LOGITS
    <blockquote>
    0.93
          
    0.88
    <start_of_image>
    0.66
        
    0.61
         
    0.61
           
    0.61
            
    0.61
    Expand
    0.60
              
    0.57
    <strong>
    0.57
    Act Density 0.001%

    No Known Activations