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

    Neuronpedia

    INDEX
    Explanations

    abstract suggestive content

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    брь
    0.39
     bebê
    0.37
     огне
    0.36
    ᆻ
    0.36
    onnaise
    0.35
    聖
    0.35
     gême
    0.34
    ፍ
    0.34
     fluids
    0.34
    <unused1049>
    0.33
    POSITIVE LOGITS
     SOS
    0.43
        
    0.39
    ↵↵
    0.37
    ------------
    0.37
                  
    0.36
                 
    0.36
    gridView
    0.36
     H
    0.35
            
    0.34
                
    0.34
    Act Density 0.003%

    No Known Activations