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

    Neuronpedia

    INDEX
    Explanations

    I'd, would, could, want

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Negative Logits
    भूषण
    0.73
     Volume
    0.69
    altungs
    0.68
     Belle
    0.65
    
    0.64
     Wilhel
    0.64
     volume
    0.63
     acquired
    0.63
     Suez
    0.63
     requisite
    0.63
    POSITIVE LOGITS
     could
    0.96
    Could
    0.94
     would
    0.92
    would
    0.89
     Could
    0.87
    could
    0.87
     могла
    0.80
     pourrait
    0.80
    Would
    0.80
     COULD
    0.78
    Act Density 0.133%

    No Known Activations