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

    Neuronpedia

    INDEX
    Explanations

    code syntax and conditions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    ীবনী
    0.94
    <unused767>
    0.91
    <unused753>
    0.89
    <unused300>
    0.89
    <unused1787>
    0.83
    <unused464>
    0.83
    <unused742>
    0.82
     gonf
    0.81
     lebt
    0.79
    <unused1916>
    0.78
    POSITIVE LOGITS
            
    0.72
    substring
    0.70
    .....
    0.70
                
    0.68
    .......
    0.68
                    
    0.67
    jTextField
    0.66
    substr
    0.66
    англ
    0.65
    .........
    0.64
    Act Density 0.027%

    No Known Activations