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

    Neuronpedia

    INDEX
    Explanations

    readability and clarity

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
     xác
    0.83
     پیچھے
    0.79
     expansion
    0.77
     ಬದಲ
    0.77
     explicação
    0.76
     explicación
    0.75
     protezione
    0.73
    expansion
    0.71
     integro
    0.70
     интегри
    0.70
    POSITIVE LOGITS
     readability
    1.49
     readable
    1.22
     whitespace
    1.10
    whitespace
    1.07
     minimalist
    1.02
     layout
    0.99
     spacing
    0.97
     Layout
    0.96
     minimalistic
    0.96
     Readable
    0.95
    Act Density 0.646%

    No Known Activations