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

    Neuronpedia

    INDEX
    Explanations

    Code snippets

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Negative Logits
    ThanOr
    -0.07
    ícul
    -0.07
     ensuite
    -0.07
     Mama
    -0.06
     Mev
    -0.06
    授
    -0.06
    When
    -0.06
    したら
    -0.06
    /sm
    -0.06
     expecting
    -0.06
    POSITIVE LOGITS
    iscal
    0.07
     участ
    0.06
    ↵    
↵
    0.06
            
↵        
↵
    0.06
    JO
    0.06
    >↵↵↵↵
    0.06
     uz
    0.06
    ursor
    0.06
    цы
    0.06
        
↵
↵
    0.06
    Act Density 0.089%

    No Known Activations